
# importing module
import pandas as pd


import seaborn as sns


# importing module
from collections import Counter


# importing module
import matplotlib.pyplot as plt


# importing module
import statistics


# importing module
import plotly.graph_objects as go


# importing module
import numpy as np


# importing module
import math


# importing module
from IPython.display import display_html


# importing module
from collections import defaultdict


# importing module
from scipy.stats import norm


# importing module
import dataframe_image as dfi


# importing module
from scipy.stats import kurtosis


# importing module
from scipy.stats import skew


# importing module
from scipy import stats


# importing module
from collections import Counter, OrderedDict


# importing module
import sqlite3


# importing module
from sklearn import linear_model


# importing module
from matplotlib.animation import FuncAnimation


# importing module
from mpl_toolkits.mplot3d import Axes3D


# importing module
import statsmodels.formula.api as smf


# importing module
%matplotlib inline


# importing module
from matplotlib import animation


# importing module
from matplotlib import cm


from sklearn.cluster import KMeans


from sklearn.preprocessing import MinMaxScaler


from sklearn.neighbors import NearestNeighbors


from sklearn import tree


from sklearn.tree import DecisionTreeClassifier


# importing module
from pandas_highcharts.core import serialize


# importing module
from pandas_highcharts.display import display_charts


# importing module
import json


%store Drama_DataFrame
%store df_data
%store system_rating_r
%store system_rating_pg
%store system_rating_pg13
%store system_rating_nc17
%store system_rating_g
%store dataframe_RIO_r
%store dataframe_RIO_pg
%store dataframe_RIO_pg13
%store dataframe_RIO_g
%store dataframe_RIO_NC
%store df_cost_r
%store freq_dis
%store cum_rel_freq
%store freq_cum_dis
%store df_roi_r
%store freq_dis_roi
%store freq_cum_dis1
%store cum_rel_freq1
%store df_roi_per_r
%store freq_dis3
%store freq_cum_dis2
%store cum_rel_freq2
%store df1
%store df2
%store df3
%store df4
%store df5
%store df_opening
%store df_month
%store df_season
%store df_4D
%store df_profit_season

Stored 'Drama_DataFrame' (DataFrame)
Stored 'df_data' (DataFrame)
Stored 'system_rating_r' (DataFrame)
Stored 'system_rating_pg' (DataFrame)
Stored 'system_rating_pg13' (DataFrame)
Stored 'system_rating_nc17' (DataFrame)
Stored 'system_rating_g' (DataFrame)
Stored 'dataframe_RIO_r' (DataFrame)
Stored 'dataframe_RIO_pg' (DataFrame)
Stored 'dataframe_RIO_pg13' (DataFrame)
Stored 'dataframe_RIO_g' (DataFrame)
Stored 'dataframe_RIO_NC' (DataFrame)
Stored 'df_cost_r' (DataFrame)
Stored 'freq_dis' (DataFrame)
Stored 'cum_rel_freq' (DataFrame)
Stored 'freq_cum_dis' (DataFrame)
Stored 'df_roi_r' (DataFrame)
Stored 'freq_dis_roi' (DataFrame)
Stored 'freq_cum_dis1' (DataFrame)
Stored 'cum_rel_freq1' (DataFrame)
Stored 'df_roi_per_r' (DataFrame)
Stored 'freq_dis3' (DataFrame)
Stored 'freq_cum_dis2' (DataFrame)
Stored 'cum_rel_freq2' (DataFrame)
Stored 'df1' (DataFrame)
Stored 'df2' (DataFrame)
Stored 'df3' (DataFrame)
Stored 'df4' (DataFrame)
Stored 'df5' (DataFrame)
Stored 'df_opening' (DataFrame)
Stored 'df_month' (DataFrame)
Stored 'df_season' (DataFrame)
Stored 'df_4D' (DataFrame)
Stored 'df_profit_season' (DataFrame)


%store -r Drama_DataFrame
%store -r df_data
%store -r system_rating_r
%store -r system_rating_pg
%store -r system_rating_pg13
%store -r system_rating_nc17
%store -r system_rating_g
%store -r dataframe_RIO_r
%store -r dataframe_RIO_pg
%store -r dataframe_RIO_pg13
%store -r dataframe_RIO_g
%store -r dataframe_RIO_NC
%store -r df_cost_r
%store -r freq_dis
%store -r cum_rel_freq
%store -r freq_cum_dis
%store -r df_roi_r
%store -r freq_dis_roi
%store -r freq_cum_dis1
%store -r cum_rel_freq1
%store -r df_roi_per_r
%store -r freq_dis3
%store -r freq_cum_dis2
%store -r cum_rel_freq2
%store -r df1
%store -r df2
%store -r df3
%store -r df4
%store -r df5
%store -r df_opening
%store -r df_month
%store -r df_season
%store -r df_4D
%store -r df_profit_season


movie_df = pd.read_csv("movies.csv")


movie_df.head()


connection = sqlite3.connect("im.db")


cursor = connection.cursor()


movie_basics_df = pd.read_sql("""SELECT * FROM movie_basics""",connection)


movie_basics_df.head()


movie_ratings_df = pd.read_sql("""SELECT * FROM movie_ratings""",connection)


movie_ratings_df.head()


movie_gross_df = pd.read_csv("bom.movie_gross (5).csv.gz")


movie_gross_df.head()


movie_budgets_df = pd.read_csv("tn.movie_budgets.csv.gz")


movie_budgets_df.head()


movie_df.columns = movie_df.columns.str.replace('name', 'movie')


movie_df.head()


movie_basics_df.columns = movie_basics_df.columns.str.replace('primary_title', 'movie')


movie_basics_df.head()


movie_gross_df.columns = movie_gross_df.columns.str.replace('title', 'movie')


movie_gross_df.head()


def common_data(list1, list2):
    result = False
  
    # traverse in the 1st list
    for x in list1:
  
        # traverse in the 2nd list
        for y in list2:
    
            # if one common
            if x == y:
                result = True
                return result 
                  
    return result


list1 = []
list2 = []
list3 = []
list4 = []
list5 = []
for i in movie_budgets_df.movie:list1.append(i)
for i in movie_gross_df.movie:list2.append(i)
for i in movie_basics_df.movie:list3.append(i)
for i in movie_budgets_df.movie:list4.append(i)
for i in movie_df.movie:list5.append(i)


len(list1)

5782


print(list1[:20])

['Avatar', 'Pirates of the Caribbean: On Stranger Tides', 'Dark Phoenix', 'Avengers: Age of Ultron', 'Star Wars Ep. VIII: The Last Jedi', 'Star Wars Ep. VII: The Force Awakens', 'Avengers: Infinity War', 'Pirates of the Caribbean: At Worldâ\x80\x99s End', 'Justice League', 'Spectre', 'The Dark Knight Rises', 'Solo: A Star Wars Story', 'The Lone Ranger', 'John Carter', 'Tangled', 'Spider-Man 3', 'Captain America: Civil War', 'Batman v Superman: Dawn of Justice', 'The Hobbit: An Unexpected Journey', 'Harry Potter and the Half-Blood Prince']


len(list2)

3387


print(list2[:20])

['Toy Story 3', 'Alice in Wonderland (2010)', 'Harry Potter and the Deathly Hallows Part 1', 'Inception', 'Shrek Forever After', 'The Twilight Saga: Eclipse', 'Iron Man 2', 'Tangled', 'Despicable Me', 'How to Train Your Dragon', 'Clash of the Titans (2010)', 'The Chronicles of Narnia: The Voyage of the Dawn Treader', "The King's Speech", 'Tron Legacy', 'The Karate Kid', 'Prince of Persia: The Sands of Time', 'Black Swan', 'Megamind', 'Robin Hood', 'The Last Airbender']


len(list3)

146144


print(list3[:20])

['Sunghursh', 'One Day Before the Rainy Season', 'The Other Side of the Wind', 'Sabse Bada Sukh', 'The Wandering Soap Opera', 'A Thin Life', 'Bigfoot', 'Joe Finds Grace', 'O Silêncio', 'Nema aviona za Zagreb', 'Pál Adrienn', 'So Much for Justice!', 'Cooper and Hemingway: The True Gen', 'Children of the Green Dragon', 'T.G.M. - osvoboditel', 'The Tragedy of Man', "How Huang Fei-hong Rescued the Orphan from the Tiger's Den", 'Heaven & Hell', 'The Final Journey', 'Los pájaros se van con la muerte']


len(list5)

7668


print(list5[:20])

['The Shining', 'The Blue Lagoon', 'Star Wars: Episode V - The Empire Strikes Back', 'Airplane!', 'Caddyshack', 'Friday the 13th', 'The Blues Brothers', 'Raging Bull', 'Superman II', 'The Long Riders', 'Any Which Way You Can', 'The Gods Must Be Crazy', 'Popeye', 'Ordinary People', 'Dressed to Kill', 'Somewhere in Time', 'Fame', '9 to 5', 'The Fog', 'Stir Crazy']


print(common_data(list5, list3),common_data(list1, list5),common_data(list5, list3),
      common_data(list3, list4))

True True True True


def commonelem_set(z, x):
    one = set(z)
    two = set(x)
    if (one & two):
        return ("There are common elements in both lists:", one & two)
    else:
        return ("There are no common elements")


len(commonelem_set(list1, list2)[1])

1238


len(commonelem_set(list1, list3)[1])

2312


len(commonelem_set(list1, list5)[1])

3551


len(commonelem_set(list2, list3)[1])

2605


movie_rating_basics = movie_ratings_df.merge(movie_basics_df,on='movie_id')


movie_rating_basics.head()


df1 = movie_budgets_df.merge(movie_gross_df,on='movie')


df1.head()


df2 = df1.merge(movie_rating_basics,on='movie')


df2.head()


df3 = df2.merge(movie_df,on='movie')


df3.head()


df3.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1262 entries, 0 to 1261
Data columns (total 31 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   id                 1262 non-null   int64  
 1   release_date       1262 non-null   object 
 2   movie              1262 non-null   object 
 3   production_budget  1262 non-null   object 
 4   domestic_gross_x   1262 non-null   object 
 5   worldwide_gross    1262 non-null   object 
 6   studio             1262 non-null   object 
 7   domestic_gross_y   1262 non-null   float64
 8   foreign_gross      1128 non-null   object 
 9   year_x             1262 non-null   int64  
 10  movie_id           1262 non-null   object 
 11  averagerating      1262 non-null   float64
 12  numvotes           1262 non-null   int64  
 13  original_title     1262 non-null   object 
 14  start_year         1262 non-null   int64  
 15  runtime_minutes    1237 non-null   float64
 16  genres             1254 non-null   object 
 17  rating             1262 non-null   object 
 18  genre              1262 non-null   object 
 19  year_y             1262 non-null   int64  
 20  released           1261 non-null   object 
 21  score              1262 non-null   float64
 22  votes              1262 non-null   float64
 23  director           1262 non-null   object 
 24  writer             1262 non-null   object 
 25  star               1262 non-null   object 
 26  country            1261 non-null   object 
 27  budget             1183 non-null   float64
 28  gross              1261 non-null   float64
 29  company            1261 non-null   object 
 30  runtime            1261 non-null   float64
dtypes: float64(8), int64(5), object(18)
memory usage: 315.5+ KB


df3 = df3.drop(['id',  'movie_id', 'numvotes', 'original_title', 'start_year', 'genres', 
          'year_y','released','score','votes','country','gross','runtime_minutes',
          'budget','domestic_gross_y'], axis=1)


df3= df3.drop(['year_x'], axis=1)


df3.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1262 entries, 0 to 1261
Data columns (total 15 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   release_date       1262 non-null   object 
 1   movie              1262 non-null   object 
 2   production_budget  1262 non-null   object 
 3   domestic_gross_x   1262 non-null   object 
 4   worldwide_gross    1262 non-null   object 
 5   studio             1262 non-null   object 
 6   foreign_gross      1128 non-null   object 
 7   averagerating      1262 non-null   float64
 8   rating             1262 non-null   object 
 9   genre              1262 non-null   object 
 10  director           1262 non-null   object 
 11  writer             1262 non-null   object 
 12  star               1262 non-null   object 
 13  company            1261 non-null   object 
 14  runtime            1261 non-null   float64
dtypes: float64(2), object(13)
memory usage: 157.8+ KB


storage1 = []
storage2 = []
production_budget_x=[]
for i in  df3.production_budget:
    storage1.append(i.replace('$',''))
for i in storage1:
    storage2.append(i.replace(',',''))
for i in storage2:   
    i = int(i)
    production_budget_x.append(i)


print(storage1[:40])

['330,600,000', '300,000,000', '300,000,000', '300,000,000', '275,000,000', '275,000,000', '275,000,000', '275,000,000', '260,000,000', '250,000,000', '250,000,000', '250,000,000', '250,000,000', '250,000,000', '250,000,000', '230,000,000', '225,000,000', '220,000,000', '220,000,000', '217,000,000', '215,000,000', '210,000,000', '210,000,000', '210,000,000', '210,000,000', '210,000,000', '210,000,000', '210,000,000', '210,000,000', '210,000,000', '99,000,000', '99,000,000', '99,000,000', '99,000,000', '99,000,000', '99,000,000', '99,000,000', '99,000,000', '200,000,000', '200,000,000']


print(production_budget_x[:40])

[330600000, 300000000, 300000000, 300000000, 275000000, 275000000, 275000000, 275000000, 260000000, 250000000, 250000000, 250000000, 250000000, 250000000, 250000000, 230000000, 225000000, 220000000, 220000000, 217000000, 215000000, 210000000, 210000000, 210000000, 210000000, 210000000, 210000000, 210000000, 210000000, 210000000, 99000000, 99000000, 99000000, 99000000, 99000000, 99000000, 99000000, 99000000, 200000000, 200000000]


len(production_budget_x)

1262


storage1 = []
storage2 = []
domestic_gross_y = []
for i in  df3.domestic_gross_x:
    storage1.append(i.replace('$',''))
for i in storage1:
    storage2.append(i.replace(',',''))
for i in storage2:   
    i = int(i)
    domestic_gross_y.append(i)


print(storage1[:40])

['459,005,868', '678,815,482', '229,024,295', '200,074,175', '448,139,099', '213,767,512', '89,302,115', '73,058,679', '200,821,936', '408,084,349', '330,360,194', '303,003,568', '258,366,855', '255,119,788', '225,764,765', '172,558,876', '291,045,518', '262,030,663', '65,233,400', '130,168,683', '652,270,625', '245,439,076', '105,487,148', '105,487,148', '105,487,148', '105,487,148', '105,487,148', '105,487,148', '105,487,148', '105,487,148', '30,824,628', '30,824,628', '30,824,628', '30,824,628', '30,824,628', '30,824,628', '30,824,628', '30,824,628', '700,059,566', '608,581,744']


print(domestic_gross_y[:40])

[459005868, 678815482, 229024295, 200074175, 448139099, 213767512, 89302115, 73058679, 200821936, 408084349, 330360194, 303003568, 258366855, 255119788, 225764765, 172558876, 291045518, 262030663, 65233400, 130168683, 652270625, 245439076, 105487148, 105487148, 105487148, 105487148, 105487148, 105487148, 105487148, 105487148, 30824628, 30824628, 30824628, 30824628, 30824628, 30824628, 30824628, 30824628, 700059566, 608581744]


len(domestic_gross_y)

1262


storage1 = []
storage2 = []
worldwide_gross_x=[]
for i in  df3.worldwide_gross:
    storage1.append(i.replace('$',''))
for i in storage1:
    storage2.append(i.replace(',',''))
for i in storage2:   
    i = int(i)
    worldwide_gross_x.append(i)


print(storage1[:40])

['1,403,013,963', '2,048,134,200', '655,945,209', '879,620,923', '1,084,439,099', '393,151,347', '260,002,115', '282,778,100', '586,477,240', '1,140,069,413', '867,500,281', '1,017,003,568', '960,366,855', '945,577,621', '1,234,846,267', '788,241,137', '667,999,518', '757,890,267', '313,477,717', '602,893,340', '1,648,854,864', '1,104,039,076', '322,459,006', '322,459,006', '322,459,006', '322,459,006', '322,459,006', '322,459,006', '322,459,006', '322,459,006', '84,747,441', '84,747,441', '84,747,441', '84,747,441', '84,747,441', '84,747,441', '84,747,441', '84,747,441', '1,348,258,224', '1,242,520,711']


print(worldwide_gross_x[:40])

[1403013963, 2048134200, 655945209, 879620923, 1084439099, 393151347, 260002115, 282778100, 586477240, 1140069413, 867500281, 1017003568, 960366855, 945577621, 1234846267, 788241137, 667999518, 757890267, 313477717, 602893340, 1648854864, 1104039076, 322459006, 322459006, 322459006, 322459006, 322459006, 322459006, 322459006, 322459006, 84747441, 84747441, 84747441, 84747441, 84747441, 84747441, 84747441, 84747441, 1348258224, 1242520711]


len(worldwide_gross_x)

1262


def isNaN(num):
    return num != num
isNaN(8)# testing the function

False


demo = []
foreign_gross_x = []
for i in df3.foreign_gross:
    if isinstance(i, str):
        if isNaN(i) == True:demo.append(i)
        if isNaN(i) == False:
            i = i.replace(",","")
            i = int(float(i))
            demo.append(i)
    else:demo.append(i)
for i in demo:
        if math.isnan(i) == True:foreign_gross_x.append(i)
        if math.isnan(i) == False:
            foreign_gross_x.append("${:,.0f}".format(i))


print(demo[:40])

[946400000, 1369, 428900000, 680600000, 636800000, 179200000, 171200000, 211100000, 391000000, 745200000, 543300000, 718100000, 700000000, 700900000, 1010, 622300000, 377000000, 495900000, 237600000, 475300000, 1019, 858600000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 646900000, 634200000]


print(foreign_gross_x[:40])

['$946,400,000', '$1,369', '$428,900,000', '$680,600,000', '$636,800,000', '$179,200,000', '$171,200,000', '$211,100,000', '$391,000,000', '$745,200,000', '$543,300,000', '$718,100,000', '$700,000,000', '$700,900,000', '$1,010', '$622,300,000', '$377,000,000', '$495,900,000', '$237,600,000', '$475,300,000', '$1,019', '$858,600,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$216,400,000', '$646,900,000', '$634,200,000']


len(foreign_gross_x)

1262


foreign_gross = []
for i in df3.foreign_gross:
    if isinstance(i, str):
        i = i.replace(",","")
        i = int(float(i))
        foreign_gross.append(i)
    else:foreign_gross.append(i)


print(foreign_gross[:40])

[946400000, 1369, 428900000, 680600000, 636800000, 179200000, 171200000, 211100000, 391000000, 745200000, 543300000, 718100000, 700000000, 700900000, 1010, 622300000, 377000000, 495900000, 237600000, 475300000, 1019, 858600000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 216400000, 646900000, 634200000]


len(foreign_gross)

1262


df3['foreign_gross']=foreign_gross
df3['worldwide_gross_x']=worldwide_gross_x
df3['foreign_gross_x']=foreign_gross_x
df3['production_budget_x']=production_budget_x
df3['domestic_gross_y']=domestic_gross_y


profit = []
for x,y in enumerate(df3.worldwide_gross_x):
    profit.append(y-df3.production_budget_x[x])
print(profit[:40]) #showing the profit list

[1072413963, 1748134200, 355945209, 579620923, 809439099, 118151347, -14997885, 7778100, 326477240, 890069413, 617500281, 767003568, 710366855, 695577621, 984846267, 558241137, 442999518, 537890267, 93477717, 385893340, 1433854864, 894039076, 112459006, 112459006, 112459006, 112459006, 112459006, 112459006, 112459006, 112459006, -14252559, -14252559, -14252559, -14252559, -14252559, -14252559, -14252559, -14252559, 1148258224, 1042520711]


len(profit)

1262


profit_x = []
for i in profit:
    profit_x.append("${:,.0f}".format(i))
print(profit_x[:40]) #showing the profit_x list

['$1,072,413,963', '$1,748,134,200', '$355,945,209', '$579,620,923', '$809,439,099', '$118,151,347', '$-14,997,885', '$7,778,100', '$326,477,240', '$890,069,413', '$617,500,281', '$767,003,568', '$710,366,855', '$695,577,621', '$984,846,267', '$558,241,137', '$442,999,518', '$537,890,267', '$93,477,717', '$385,893,340', '$1,433,854,864', '$894,039,076', '$112,459,006', '$112,459,006', '$112,459,006', '$112,459,006', '$112,459,006', '$112,459,006', '$112,459,006', '$112,459,006', '$-14,252,559', '$-14,252,559', '$-14,252,559', '$-14,252,559', '$-14,252,559', '$-14,252,559', '$-14,252,559', '$-14,252,559', '$1,148,258,224', '$1,042,520,711']


len(profit_x)

1262


no_tickets = []
for i in df3.worldwide_gross_x:
    no_tickets.append(round(i/10))
print(no_tickets[:40]) #showing the no_tickets list

[140301396, 204813420, 65594521, 87962092, 108443910, 39315135, 26000212, 28277810, 58647724, 114006941, 86750028, 101700357, 96036686, 94557762, 123484627, 78824114, 66799952, 75789027, 31347772, 60289334, 164885486, 110403908, 32245901, 32245901, 32245901, 32245901, 32245901, 32245901, 32245901, 32245901, 8474744, 8474744, 8474744, 8474744, 8474744, 8474744, 8474744, 8474744, 134825822, 124252071]


len(no_tickets)

1262


str_tickets = [] 
for i in no_tickets:
    str_tickets.append("{:,.0f}".format(i))
print(str_tickets[:40]) #showing the str_tickets list

['140,301,396', '204,813,420', '65,594,521', '87,962,092', '108,443,910', '39,315,135', '26,000,212', '28,277,810', '58,647,724', '114,006,941', '86,750,028', '101,700,357', '96,036,686', '94,557,762', '123,484,627', '78,824,114', '66,799,952', '75,789,027', '31,347,772', '60,289,334', '164,885,486', '110,403,908', '32,245,901', '32,245,901', '32,245,901', '32,245,901', '32,245,901', '32,245,901', '32,245,901', '32,245,901', '8,474,744', '8,474,744', '8,474,744', '8,474,744', '8,474,744', '8,474,744', '8,474,744', '8,474,744', '134,825,822', '124,252,071']


len(str_tickets)

1262


df3['Profit']=profit
df3['Profit_x']=profit_x
df3['Tickets']=no_tickets
df3['Tickets_x']=str_tickets


df3.head()


df3.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1262 entries, 0 to 1261
Data columns (total 23 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   release_date         1262 non-null   object 
 1   movie                1262 non-null   object 
 2   production_budget    1262 non-null   object 
 3   domestic_gross_x     1262 non-null   object 
 4   worldwide_gross      1262 non-null   object 
 5   studio               1262 non-null   object 
 6   foreign_gross        1128 non-null   float64
 7   averagerating        1262 non-null   float64
 8   rating               1262 non-null   object 
 9   genre                1262 non-null   object 
 10  director             1262 non-null   object 
 11  writer               1262 non-null   object 
 12  star                 1262 non-null   object 
 13  company              1261 non-null   object 
 14  runtime              1261 non-null   float64
 15  worldwide_gross_x    1262 non-null   int64  
 16  foreign_gross_x      1128 non-null   object 
 17  production_budget_x  1262 non-null   int64  
 18  domestic_gross_y     1262 non-null   int64  
 19  Profit               1262 non-null   int64  
 20  Profit_x             1262 non-null   object 
 21  Tickets              1262 non-null   int64  
 22  Tickets_x            1262 non-null   object 
dtypes: float64(3), int64(5), object(15)
memory usage: 268.9+ KB


df3 = df3[['movie','release_date','genre','rating','production_budget_x','production_budget',
           'domestic_gross_y','domestic_gross_x','foreign_gross','foreign_gross_x','worldwide_gross',
           'worldwide_gross_x','Profit','Profit_x','Tickets','Tickets_x','runtime','averagerating',
           'company','studio','star','director','writer']]


df3.head()


df3.columns = ['Movie','Release_Date','Genre','Rating','Production_Budget','Production_Budget_x',
           'Domestic_Gross','Domestic_Gross_x','Foreign_Gross','Foreign_Gross_x','Worldwide_Gross',
           'Worldwide_Gross_x','Profit','Profit_x','Tickets','Tickets_x','Runtime','Averagerating',
            'Company','Studio','Star','Director','Writer']


df3.head()


# putting movies into groups
grouped = []
for i in df3.Genre:
    grouped.append(i)
grouped=Counter(grouped)
grouped

Counter({'Action': 404,
         'Animation': 92,
         'Adventure': 61,
         'Drama': 200,
         'Comedy': 243,
         'Biography': 118,
         'Horror': 63,
         'Crime': 66,
         'Mystery': 2,
         'Romance': 1,
         'Fantasy': 8,
         'Sci-Fi': 3,
         'Thriller': 1})


# putting movies into groups
grouped1 = []
for i in df3.Rating:
    grouped1.append(i)
grouped1= Counter(grouped1)
grouped1

Counter({'PG-13': 534,
         'PG': 161,
         'G': 9,
         'R': 544,
         'Not Rated': 11,
         'Unrated': 1,
         'NC-17': 2})


drama_index = []
for i,x in enumerate(df3.Genre):
    if x == 'Drama':drama_index.append(i)
print(drama_index) #showing the drama_index list

[65, 66, 128, 188, 203, 273, 308, 322, 328, 347, 349, 365, 368, 373, 374, 376, 380, 391, 398, 407, 412, 417, 418, 419, 421, 422, 428, 447, 463, 475, 508, 511, 512, 514, 520, 526, 527, 528, 530, 531, 532, 534, 537, 540, 542, 575, 582, 590, 593, 605, 608, 610, 629, 646, 659, 675, 681, 686, 690, 694, 696, 715, 716, 741, 746, 751, 755, 756, 767, 768, 772, 773, 776, 781, 783, 797, 798, 808, 809, 810, 820, 821, 834, 850, 851, 852, 853, 854, 857, 867, 868, 869, 873, 878, 888, 902, 906, 907, 908, 909, 910, 911, 917, 918, 925, 929, 934, 936, 937, 939, 966, 970, 971, 972, 973, 975, 978, 979, 980, 983, 992, 995, 1005, 1006, 1030, 1031, 1032, 1037, 1038, 1040, 1041, 1050, 1053, 1070, 1072, 1073, 1074, 1079, 1081, 1083, 1084, 1087, 1105, 1106, 1107, 1108, 1121, 1123, 1125, 1130, 1132, 1136, 1138, 1139, 1140, 1142, 1143, 1145, 1146, 1148, 1149, 1151, 1152, 1154, 1155, 1157, 1158, 1162, 1166, 1173, 1177, 1178, 1182, 1187, 1198, 1205, 1207, 1209, 1210, 1211, 1213, 1215, 1216, 1217, 1219, 1220, 1229, 1232, 1233, 1239, 1243, 1244, 1245, 1246, 1254, 1255, 1256, 1257, 1258, 1261]


len(drama_index)

200


demo_df = df3.iloc[drama_index]

['Hugo', 'Hugo', 'The Wolfman', 'Gravity', 'Django Unchained', 'Sing', 'Downsizing', 'Gone Girl', 'Contagion', 'Trouble with the Curve', 'Priest', 'Fifty Shades Darker', 'Fifty Shades Freed', 'Burlesque', 'Burlesque', 'Crimson Peak', 'Zero Dark Thirty', 'Creed II', 'The Post', 'Hereafter', 'Dream House', 'Upside Down', 'Upside Down', 'Upside Down', 'Anna Karenina', 'Anna Karenina', 'Arrival', 'Charlie St. Cloud', 'Fifty Shades of Grey', 'Bridge of Spies', 'The Impossible', 'Paranoia', 'Paranoia', 'Victor Frankenstein', 'Water for Elephants', 'The Master', 'The Master', 'The Master', 'Creed', 'Creed', 'Creed', 'Dolphin Tale', 'The Rite', 'Collateral Beauty', 'True Grit', 'The Tree of Life', 'Biutiful', 'The Longest Ride', 'Step Up Revolution', 'Flight', 'Extraordinary Measures', 'The Vow', 'The Age of Adaline', 'The Space Between Us', 'Safe Haven', 'Anonymous', 'The Best of Me', 'The Help', 'Dear John', 'The Lucky One', 'The Giver', 'Draft Day', 'Rings', 'Tulip Fever', 'Fences', 'The Ides of March', 'Nocturnal Animals', 'The Water Diviner', 'Stone', 'Stone', 'For Colored Girls', 'The Beaver', 'Wonder', 'The Last Song', 'Me Before You', 'The Debt', 'The Debt', 'The Light Between Oceans', 'Let Me In', 'Let Me In', 'By the Sea', 'By the Sea', 'The Book Thief', 'Labor Day', 'Midnight Special', 'Miss Sloane', 'A Quiet Place', 'A Quiet Place', 'Beastly', 'The Roommate', 'Remember Me', 'Remember Me', 'The Homesman', 'The Immigrant', 'The Woman in Black', 'Country Strong', 'One Day', 'One Day', 'One Day', 'One Day', 'One Day', 'One Day', 'Never Let Me Go', 'The Reluctant Fundamentalist', 'Suffragette', 'Black Swan', 'Ex Machina', 'The Perks of Being a Wallflower', 'Room', 'Chloe', 'Project Almanac', 'If Beale Street Could Talk', 'Wish Upon', 'Arbitrage', 'Stoker', 'Carol', 'If I Stay', 'Brooklyn', 'Brooklyn', 'Quartet', 'Hereditary', 'Everything, Everything', 'Mud', 'Mud', 'Coriolanus', 'Coriolanus', 'Amour', 'Melancholia', 'Melancholia', 'Ouija: Origin of Evil', 'Black or White', 'Manchester by the Sea', 'Yeh Jawaani Hai Deewani', 'The Bye Bye Man', 'Gifted', 'Gifted', 'Gifted', 'We Need to Talk About Kevin', 'Hesher', 'Shame', 'Shame', 'The Words', 'Lights Out', 'Lights Out', 'Lights Out', 'Lights Out', 'Still Alice', 'Addicted', 'Before I Fall', 'Everything Must Go', 'Rabbit Hole', 'Mommy', 'Take Shelter', 'Maggie', 'Maggie', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Boyhood', 'Stake Land', 'The Witch', 'Margin Call', 'Whiplash', 'War Room', 'Before Midnight', 'Ida', 'Courageous', 'Silent House', "Winter's Bone", 'The Florida Project', 'We Are Your Friends', 'Locke', 'The Babadook', 'Knock Knock', 'Knock Knock', 'Buried', 'Buried', 'The Lunchbox', 'Unsane', 'Mustang', 'Blue Valentine', 'Martha Marcy May Marlene', 'Palo Alto', 'I Origins', 'The Invitation', 'Like Crazy', 'Like Crazy', 'The Canyons', 'Another Earth', 'Sound of My Voice', 'A Ghost Story']

[('A Quiet Place', [86, 87]),
 ('Anna', [155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166]),
 ('Anna Karenina', [24, 25]),
 ('Brooklyn', [117, 118]),
 ('Buried', [184, 185]),
 ('Burlesque', [13, 14]),
 ('By the Sea', [80, 81]),
 ('Coriolanus', [124, 125]),
 ('Creed', [38, 39, 40]),
 ('Gifted', [134, 135, 136]),
 ('Hugo', [0, 1]),
 ('Knock Knock', [182, 183]),
 ('Let Me In', [78, 79]),
 ('Lights Out', [142, 143, 144, 145]),
 ('Like Crazy', [194, 195]),
 ('Maggie', [153, 154]),
 ('Melancholia', [127, 128]),
 ('Mud', [122, 123]),
 ('One Day', [96, 97, 98, 99, 100, 101]),
 ('Paranoia', [31, 32]),
 ('Remember Me', [90, 91]),
 ('Shame', [139, 140]),
 ('Stone', [68, 69]),
 ('The Debt', [75, 76]),
 ('The Master', [35, 36, 37]),
 ('Upside Down', [21, 22, 23])]

[87]
[156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166]
[25]
[118]
[185]
[14]
[81]
[125]
[39, 40]
[135, 136]
[1]
[183]
[79]
[143, 144, 145]
[195]
[154]
[128]
[123]
[97, 98, 99, 100, 101]
[32]
[91]
[140]
[69]
[76]
[36, 37]
[22, 23]

[87, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 25, 118, 185, 14, 81, 125, 39, 40, 135, 136, 1, 183, 79, 143, 144, 145, 195, 154, 128, 123, 97, 98, 99, 100, 101, 32, 91, 140, 69, 76, 36, 37, 22, 23]

46

Counter({'PG': 7, 'R': 67, 'PG-13': 76, 'Not Rated': 3, 'NC-17': 1})

Counter({'R': 767,
         'PG': 155,
         nan: 35,
         'G': 11,
         'Not Rated': 113,
         'PG-13': 390,
         'Unrated': 27,
         'NC-17': 14,
         'X': 1,
         'TV-PG': 2,
         'TV-MA': 3})

[15, 24, 33, 38, 61, 63, 64, 114, 116, 119, 135, 150, 170, 225, 265, 297, 312, 339, 373, 382, 411, 458, 461, 473, 488, 503, 527, 560, 561, 583, 606, 621, 630, 663, 776, 793, 805, 815, 841, 897, 908, 1026, 1037, 1217, 1230, 1235, 1241, 1287, 1311, 1377, 1387, 1399, 1447, 1492, 1499, 1572, 1706, 1756, 1779, 1811, 1821, 1840, 1953, 2025, 2036, 2070, 2081, 2104, 2126, 2278, 2280, 2286, 2461, 2539, 2664, 2710, 2730, 2813, 2829, 2938, 2993, 3029, 3056, 3186, 3371, 3609, 3963, 4078, 4145, 4834, 4950, 4971, 4979, 4981, 5075, 5139, 5406, 5765, 5813, 5828, 6600, 6662, 6840, 7065, 7447, 7577]

106

[13, 16, 81, 107, 143, 146, 160, 174, 180, 181, 188, 193, 211, 236, 248, 257, 273, 285, 304, 343, 348, 368, 408, 409, 415, 427, 443, 450, 454, 525, 533, 544, 553, 570, 585, 608, 610, 616, 620, 627, 631, 654, 656, 676, 697, 698, 741, 757, 784, 795, 802, 852, 853, 856, 861, 868, 870, 876, 911, 924, 951, 961, 962, 992, 1006, 1035, 1040, 1057, 1143, 1166, 1181, 1188, 1196, 1197, 1207, 1208, 1226, 1236, 1247, 1274, 1283, 1336, 1337, 1339, 1343, 1358, 1365, 1391, 1405, 1408, 1416, 1418, 1423, 1428, 1442, 1457, 1483, 1518, 1564, 1570, 1574, 1575, 1594, 1608, 1635, 1652, 1660, 1665, 1685, 1687, 1723, 1735, 1736, 1738, 1750, 1752, 1760, 1761, 1787, 1819, 1831, 1832, 1834, 1857, 1867, 1872, 1876, 1903, 1916, 1925, 1930, 1944, 1964, 1965, 1975, 1979, 1998, 1999, 2031, 2033, 2034, 2044, 2049, 2050, 2053, 2065, 2080, 2085, 2138, 2155, 2159, 2182, 2189, 2191, 2217, 2218, 2227, 2231, 2261, 2276, 2293, 2299, 2315, 2323, 2332, 2337, 2338, 2346, 2361, 2368, 2369, 2383, 2413, 2425, 2432, 2439, 2443, 2454, 2457, 2476, 2478, 2501, 2502, 2514, 2536, 2552, 2606, 2660, 2662, 2703, 2747, 2758, 2771, 2775, 2782, 2783, 2793, 2810, 2860, 2863, 2865, 2869, 2889, 2936, 2942, 2966, 3003, 3007, 3010, 3011, 3036, 3039, 3043, 3044, 3049, 3121, 3127, 3141, 3150, 3164, 3165, 3166, 3176, 3183, 3188, 3197, 3201, 3236, 3239, 3244, 3245, 3264, 3291, 3302, 3313, 3320, 3366, 3377, 3391, 3398, 3401, 3413, 3450, 3458, 3460, 3461, 3497, 3498, 3505, 3552, 3563, 3567, 3572, 3581, 3583, 3621, 3634, 3700, 3740, 3744, 3762, 3776, 3789, 3793, 3795, 3796, 3832, 3833, 3850, 3855, 3903, 3925, 3941, 3943, 3961, 3974, 3987, 3994, 4024, 4032, 4039, 4045, 4074, 4105, 4109, 4118, 4126, 4148, 4167, 4197, 4241, 4262, 4272, 4333, 4357, 4361, 4411, 4438, 4449, 4450, 4468, 4480, 4489, 4494, 4505, 4547, 4568, 4599, 4621, 4649, 4672, 4762, 4763, 4796, 4797, 4810, 4818, 4822, 4831, 4856, 4909, 4914, 4920, 4961, 5010, 5043, 5070, 5106, 5163, 5167, 5187, 5189, 5198, 5217, 5218, 5223, 5225, 5234, 5242, 5258, 5272, 5275, 5276, 5317, 5362, 5385, 5386, 5401, 5416, 5489, 5508, 5511, 5523, 5533, 5538, 5559, 5574, 5620, 5640, 5650, 5676, 5691, 5711, 5798, 5799, 5805, 5820, 5835, 5836, 5840, 5842, 5846, 5915, 5916, 5950, 5984, 5990, 5997, 6044, 6057, 6065, 6068, 6134, 6147, 6170, 6186, 6192, 6212, 6213, 6231, 6236, 6258, 6323, 6335, 6362, 6402, 6405, 6408, 6412, 6426, 6447, 6450, 6489, 6512, 6540, 6553, 6575, 6587, 6610, 6635, 6638, 6649, 6669, 6710, 6735, 6868, 6891, 6893, 6897, 6927, 6985, 7005, 7039, 7067, 7085, 7092, 7098, 7102, 7117, 7132, 7142, 7147, 7156, 7172, 7173, 7180, 7193, 7196, 7217, 7234, 7248, 7267, 7279, 7331, 7378, 7408, 7418, 7422, 7443, 7461, 7462, 7495, 7507, 7513, 7530, 7550, 7592, 7593, 7658, 7661]


demo_df = df3.iloc[drama_index]


demo_df = demo_df.reset_index(drop=True)


demo_df


demo_name = []
for i,x in enumerate(demo_df.Movie):demo_name.append(x)
print(demo_name) #showing the demo_name list

['Hugo', 'Hugo', 'The Wolfman', 'Gravity', 'Django Unchained', 'Sing', 'Downsizing', 'Gone Girl', 'Contagion', 'Trouble with the Curve', 'Priest', 'Fifty Shades Darker', 'Fifty Shades Freed', 'Burlesque', 'Burlesque', 'Crimson Peak', 'Zero Dark Thirty', 'Creed II', 'The Post', 'Hereafter', 'Dream House', 'Upside Down', 'Upside Down', 'Upside Down', 'Anna Karenina', 'Anna Karenina', 'Arrival', 'Charlie St. Cloud', 'Fifty Shades of Grey', 'Bridge of Spies', 'The Impossible', 'Paranoia', 'Paranoia', 'Victor Frankenstein', 'Water for Elephants', 'The Master', 'The Master', 'The Master', 'Creed', 'Creed', 'Creed', 'Dolphin Tale', 'The Rite', 'Collateral Beauty', 'True Grit', 'The Tree of Life', 'Biutiful', 'The Longest Ride', 'Step Up Revolution', 'Flight', 'Extraordinary Measures', 'The Vow', 'The Age of Adaline', 'The Space Between Us', 'Safe Haven', 'Anonymous', 'The Best of Me', 'The Help', 'Dear John', 'The Lucky One', 'The Giver', 'Draft Day', 'Rings', 'Tulip Fever', 'Fences', 'The Ides of March', 'Nocturnal Animals', 'The Water Diviner', 'Stone', 'Stone', 'For Colored Girls', 'The Beaver', 'Wonder', 'The Last Song', 'Me Before You', 'The Debt', 'The Debt', 'The Light Between Oceans', 'Let Me In', 'Let Me In', 'By the Sea', 'By the Sea', 'The Book Thief', 'Labor Day', 'Midnight Special', 'Miss Sloane', 'A Quiet Place', 'A Quiet Place', 'Beastly', 'The Roommate', 'Remember Me', 'Remember Me', 'The Homesman', 'The Immigrant', 'The Woman in Black', 'Country Strong', 'One Day', 'One Day', 'One Day', 'One Day', 'One Day', 'One Day', 'Never Let Me Go', 'The Reluctant Fundamentalist', 'Suffragette', 'Black Swan', 'Ex Machina', 'The Perks of Being a Wallflower', 'Room', 'Chloe', 'Project Almanac', 'If Beale Street Could Talk', 'Wish Upon', 'Arbitrage', 'Stoker', 'Carol', 'If I Stay', 'Brooklyn', 'Brooklyn', 'Quartet', 'Hereditary', 'Everything, Everything', 'Mud', 'Mud', 'Coriolanus', 'Coriolanus', 'Amour', 'Melancholia', 'Melancholia', 'Ouija: Origin of Evil', 'Black or White', 'Manchester by the Sea', 'Yeh Jawaani Hai Deewani', 'The Bye Bye Man', 'Gifted', 'Gifted', 'Gifted', 'We Need to Talk About Kevin', 'Hesher', 'Shame', 'Shame', 'The Words', 'Lights Out', 'Lights Out', 'Lights Out', 'Lights Out', 'Still Alice', 'Addicted', 'Before I Fall', 'Everything Must Go', 'Rabbit Hole', 'Mommy', 'Take Shelter', 'Maggie', 'Maggie', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Anna', 'Boyhood', 'Stake Land', 'The Witch', 'Margin Call', 'Whiplash', 'War Room', 'Before Midnight', 'Ida', 'Courageous', 'Silent House', "Winter's Bone", 'The Florida Project', 'We Are Your Friends', 'Locke', 'The Babadook', 'Knock Knock', 'Knock Knock', 'Buried', 'Buried', 'The Lunchbox', 'Unsane', 'Mustang', 'Blue Valentine', 'Martha Marcy May Marlene', 'Palo Alto', 'I Origins', 'The Invitation', 'Like Crazy', 'Like Crazy', 'The Canyons', 'Another Earth', 'Sound of My Voice', 'A Ghost Story']


def list_duplicates(seq):
    tally = defaultdict(list)
    for i,item in enumerate(seq):
        tally[item].append(i)
    return ((key,locs) for key,locs in tally.items() 
                            if len(locs)>1)


demo_dup = []
for dup in sorted(list_duplicates(demo_name)):
    demo_dup.append(dup)


demo_dup

[('A Quiet Place', [86, 87]),
 ('Anna', [155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166]),
 ('Anna Karenina', [24, 25]),
 ('Brooklyn', [117, 118]),
 ('Buried', [184, 185]),
 ('Burlesque', [13, 14]),
 ('By the Sea', [80, 81]),
 ('Coriolanus', [124, 125]),
 ('Creed', [38, 39, 40]),
 ('Gifted', [134, 135, 136]),
 ('Hugo', [0, 1]),
 ('Knock Knock', [182, 183]),
 ('Let Me In', [78, 79]),
 ('Lights Out', [142, 143, 144, 145]),
 ('Like Crazy', [194, 195]),
 ('Maggie', [153, 154]),
 ('Melancholia', [127, 128]),
 ('Mud', [122, 123]),
 ('One Day', [96, 97, 98, 99, 100, 101]),
 ('Paranoia', [31, 32]),
 ('Remember Me', [90, 91]),
 ('Shame', [139, 140]),
 ('Stone', [68, 69]),
 ('The Debt', [75, 76]),
 ('The Master', [35, 36, 37]),
 ('Upside Down', [21, 22, 23])]


for i in demo_dup:print(i[1][1:])

[87]
[156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166]
[25]
[118]
[185]
[14]
[81]
[125]
[39, 40]
[135, 136]
[1]
[183]
[79]
[143, 144, 145]
[195]
[154]
[128]
[123]
[97, 98, 99, 100, 101]
[32]
[91]
[140]
[69]
[76]
[36, 37]
[22, 23]


demo_dup_index = []
for i in demo_dup:demo_dup_index+=i[1][1:]
print(demo_dup_index) #showing the demo_dup_index list

[87, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 25, 118, 185, 14, 81, 125, 39, 40, 135, 136, 1, 183, 79, 143, 144, 145, 195, 154, 128, 123, 97, 98, 99, 100, 101, 32, 91, 140, 69, 76, 36, 37, 22, 23]


len(demo_dup_index)

46


demo_df = demo_df.drop(demo_dup_index)
Drama_df = demo_df.reset_index(drop=True)#reseting the index


grouped1 = []
for i in Drama_df.Rating:
    grouped1.append(i)
grouped1= Counter(grouped1)
grouped1

Counter({'PG': 7, 'R': 67, 'PG-13': 76, 'Not Rated': 3, 'NC-17': 1})


Drama_df


grouped1 = []
for i,x in enumerate(movie_df.rating):
    if movie_df.genre[i] == 'Drama':grouped1.append(movie_df.rating[i])
grouped1=collections.Counter(grouped1)
grouped1

Counter({'R': 767,
         'PG': 155,
         nan: 35,
         'G': 11,
         'Not Rated': 113,
         'PG-13': 390,
         'Unrated': 27,
         'NC-17': 14,
         'X': 1,
         'TV-PG': 2,
         'TV-MA': 3})


index_pg = []
for i,x in enumerate(movie_df.genre):
    if x =='Drama' and movie_df.rating[i] == 'PG' and movie_df.country[i] == 'United States':
        index_pg.append(i)
print(index_pg) #showing the index_pg list

[15, 24, 33, 38, 61, 63, 64, 114, 116, 119, 135, 150, 170, 225, 265, 297, 312, 339, 373, 382, 411, 458, 461, 473, 488, 503, 527, 560, 561, 583, 606, 621, 630, 663, 776, 793, 805, 815, 841, 897, 908, 1026, 1037, 1217, 1230, 1235, 1241, 1287, 1311, 1377, 1387, 1399, 1447, 1492, 1499, 1572, 1706, 1756, 1779, 1811, 1821, 1840, 1953, 2025, 2036, 2070, 2081, 2104, 2126, 2278, 2280, 2286, 2461, 2539, 2664, 2710, 2730, 2813, 2829, 2938, 2993, 3029, 3056, 3186, 3371, 3609, 3963, 4078, 4145, 4834, 4950, 4971, 4979, 4981, 5075, 5139, 5406, 5765, 5813, 5828, 6600, 6662, 6840, 7065, 7447, 7577]


len(index_pg)

106


index_r = []
for i,x in enumerate(movie_df.genre):
    if x =='Drama' and movie_df.rating[i] == 'R'and movie_df.country[i] == 'United States':
        index_r.append(i)
print(index_r) #showing the index_r list

[13, 16, 81, 107, 143, 146, 160, 174, 180, 181, 188, 193, 211, 236, 248, 257, 273, 285, 304, 343, 348, 368, 408, 409, 415, 427, 443, 450, 454, 525, 533, 544, 553, 570, 585, 608, 610, 616, 620, 627, 631, 654, 656, 676, 697, 698, 741, 757, 784, 795, 802, 852, 853, 856, 861, 868, 870, 876, 911, 924, 951, 961, 962, 992, 1006, 1035, 1040, 1057, 1143, 1166, 1181, 1188, 1196, 1197, 1207, 1208, 1226, 1236, 1247, 1274, 1283, 1336, 1337, 1339, 1343, 1358, 1365, 1391, 1405, 1408, 1416, 1418, 1423, 1428, 1442, 1457, 1483, 1518, 1564, 1570, 1574, 1575, 1594, 1608, 1635, 1652, 1660, 1665, 1685, 1687, 1723, 1735, 1736, 1738, 1750, 1752, 1760, 1761, 1787, 1819, 1831, 1832, 1834, 1857, 1867, 1872, 1876, 1903, 1916, 1925, 1930, 1944, 1964, 1965, 1975, 1979, 1998, 1999, 2031, 2033, 2034, 2044, 2049, 2050, 2053, 2065, 2080, 2085, 2138, 2155, 2159, 2182, 2189, 2191, 2217, 2218, 2227, 2231, 2261, 2276, 2293, 2299, 2315, 2323, 2332, 2337, 2338, 2346, 2361, 2368, 2369, 2383, 2413, 2425, 2432, 2439, 2443, 2454, 2457, 2476, 2478, 2501, 2502, 2514, 2536, 2552, 2606, 2660, 2662, 2703, 2747, 2758, 2771, 2775, 2782, 2783, 2793, 2810, 2860, 2863, 2865, 2869, 2889, 2936, 2942, 2966, 3003, 3007, 3010, 3011, 3036, 3039, 3043, 3044, 3049, 3121, 3127, 3141, 3150, 3164, 3165, 3166, 3176, 3183, 3188, 3197, 3201, 3236, 3239, 3244, 3245, 3264, 3291, 3302, 3313, 3320, 3366, 3377, 3391, 3398, 3401, 3413, 3450, 3458, 3460, 3461, 3497, 3498, 3505, 3552, 3563, 3567, 3572, 3581, 3583, 3621, 3634, 3700, 3740, 3744, 3762, 3776, 3789, 3793, 3795, 3796, 3832, 3833, 3850, 3855, 3903, 3925, 3941, 3943, 3961, 3974, 3987, 3994, 4024, 4032, 4039, 4045, 4074, 4105, 4109, 4118, 4126, 4148, 4167, 4197, 4241, 4262, 4272, 4333, 4357, 4361, 4411, 4438, 4449, 4450, 4468, 4480, 4489, 4494, 4505, 4547, 4568, 4599, 4621, 4649, 4672, 4762, 4763, 4796, 4797, 4810, 4818, 4822, 4831, 4856, 4909, 4914, 4920, 4961, 5010, 5043, 5070, 5106, 5163, 5167, 5187, 5189, 5198, 5217, 5218, 5223, 5225, 5234, 5242, 5258, 5272, 5275, 5276, 5317, 5362, 5385, 5386, 5401, 5416, 5489, 5508, 5511, 5523, 5533, 5538, 5559, 5574, 5620, 5640, 5650, 5676, 5691, 5711, 5798, 5799, 5805, 5820, 5835, 5836, 5840, 5842, 5846, 5915, 5916, 5950, 5984, 5990, 5997, 6044, 6057, 6065, 6068, 6134, 6147, 6170, 6186, 6192, 6212, 6213, 6231, 6236, 6258, 6323, 6335, 6362, 6402, 6405, 6408, 6412, 6426, 6447, 6450, 6489, 6512, 6540, 6553, 6575, 6587, 6610, 6635, 6638, 6649, 6669, 6710, 6735, 6868, 6891, 6893, 6897, 6927, 6985, 7005, 7039, 7067, 7085, 7092, 7098, 7102, 7117, 7132, 7142, 7147, 7156, 7172, 7173, 7180, 7193, 7196, 7217, 7234, 7248, 7267, 7279, 7331, 7378, 7408, 7418, 7422, 7443, 7461, 7462, 7495, 7507, 7513, 7530, 7550, 7592, 7593, 7658, 7661]


len(index_r)

460


index_g = []
for i,x in enumerate(movie_df.genre):
    if x =='Drama' and movie_df.rating[i] == 'G':index_g.append(i)
print(index_g) #showing the index_g list

[321, 629, 1124, 1218, 1622, 1901, 2283, 2580, 2706, 3624, 4146]


len(index_g)

11


index_nc = []
for i,x in enumerate(movie_df.genre):
    if x =='Drama' and movie_df.rating[i] == 'NC-17':index_nc.append(i)
print(index_nc) #showing the index_nc list

[926, 1946, 2170, 2393, 2653, 2661, 2856, 3175, 4257, 4609, 5112, 5872, 6029, 6256]


len(index_nc)

14


for i,x in enumerate(Drama_df.Movie):
    if Drama_df.Rating[i]=='PG':print(x)

Hugo
Dolphin Tale
Extraordinary Measures
Wonder
The Last Song
War Room
The Lunchbox


demo_pg = movie_df.iloc[index_pg]
demo_pg = demo_pg.reset_index(drop=True)


demo_pg.head()


demo_nc = movie_df.iloc[index_nc]
demo_nc = demo_nc.reset_index(drop=True)


demo_nc


demo_r = movie_df.iloc[index_r]
demo_r = demo_r.reset_index(drop=True)
demo_r = demo_r[:11]


demo_r


demo_g = movie_df.iloc[index_g]
demo_g = demo_g.reset_index(drop=True)


demo_g


demo_pg_index = [0,1,101,102,103,104,105,3,2,86,87,88,89,90,91,92,93,94,95,
                96,97,98,100,75,76,77,78,79,82,83,85,74,73,71,70,69,68,67,66,65,
                5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,24,25]
print(demo_pg_index) #showing the demo_pg_index list

[0, 1, 101, 102, 103, 104, 105, 3, 2, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 100, 75, 76, 77, 78, 79, 82, 83, 85, 74, 73, 71, 70, 69, 68, 67, 66, 65, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25]


len(demo_pg_index)

60


worldwide_pg = [9709597, 46918287,542351353,73986904,305937718,216601214,38102988,27118000,
            534816,37306334,47494916,19344615,38741732,114830111,43545364,18948425,3438735,
            137587063,64605762,33473297,89137047,8526288,64667874,106269971,35656130,3987768,
            7025496,152036382,171120329,13835130,14859394,134582776,6101815,
            63954968,10769960,32255440,15164458,127956187,2819485,43440294,17815212,157297525,
            35856053,119285432,40716963,14920781,3281232,14923752,125052686,549368315,6668025,199078,
            64892670,4786789,8443124,2044892,2400000,1705908,80008942,48000000]
print(worldwide_pg) #showing the worldwide_pg list

[9709597, 46918287, 542351353, 73986904, 305937718, 216601214, 38102988, 27118000, 534816, 37306334, 47494916, 19344615, 38741732, 114830111, 43545364, 18948425, 3438735, 137587063, 64605762, 33473297, 89137047, 8526288, 64667874, 106269971, 35656130, 3987768, 7025496, 152036382, 171120329, 13835130, 14859394, 134582776, 6101815, 63954968, 10769960, 32255440, 15164458, 127956187, 2819485, 43440294, 17815212, 157297525, 35856053, 119285432, 40716963, 14920781, 3281232, 14923752, 125052686, 549368315, 6668025, 199078, 64892670, 4786789, 8443124, 2044892, 2400000, 1705908, 80008942, 48000000]


len(worldwide_pg)

60


domestic_pg = [0,0,201151353,67790117,132422809,108101214,34700142,0,0,27796042,41281092,19161999,
              32751093,52330111,0,18848430,0,82272442,31664162,33456317,62950384,3493000,60705732,82569971,
              0,0,0,104636382,100920329,10162034,0,43182776,0,22954968,0,0,0,55956187,0,0,0,37686805,
              0,0,0,0,0,0,125049125,218815487,0,0,0,0,0,1537122,0,705908,80000000,0]
print(domestic_pg) #showing the domestic_pg list

[0, 0, 201151353, 67790117, 132422809, 108101214, 34700142, 0, 0, 27796042, 41281092, 19161999, 32751093, 52330111, 0, 18848430, 0, 82272442, 31664162, 33456317, 62950384, 3493000, 60705732, 82569971, 0, 0, 0, 104636382, 100920329, 10162034, 0, 43182776, 0, 22954968, 0, 0, 0, 55956187, 0, 0, 0, 37686805, 0, 0, 0, 0, 0, 0, 125049125, 218815487, 0, 0, 0, 0, 0, 1537122, 0, 705908, 80000000, 0]


len(domestic_pg)

60


foreign_pg = []
for i,x in enumerate(worldwide_pg):
    if domestic_pg[i] == 0:foreign_pg.append(0)
    else:foreign_pg.append(x-domestic_pg[i])
print(foreign_pg) #showing the foreign_pg list

[0, 0, 341200000, 6196787, 173514909, 108500000, 3402846, 0, 0, 9510292, 6213824, 182616, 5990639, 62500000, 0, 99995, 0, 55314621, 32941600, 16980, 26186663, 5033288, 3962142, 23700000, 0, 0, 0, 47400000, 70200000, 3673096, 0, 91400000, 0, 41000000, 0, 0, 0, 72000000, 0, 0, 0, 119610720, 0, 0, 0, 0, 0, 0, 3561, 330552828, 0, 0, 0, 0, 0, 507770, 0, 1000000, 8942, 0]


len(foreign_pg)

60


demo1_pg = demo_pg.iloc[demo_pg_index]


demo1_pg = demo1_pg.reset_index(drop=True)


demo1_pg.head()


demo1_pg = demo1_pg.fillna(0)


demo1_pg.head()


nan_index = []
for i,x in enumerate(demo1_pg.budget):
    if x == 0.0 :nan_index.append(i)
print(nan_index) #showing the nan_index list

[1, 7, 16, 21, 37, 40, 41, 43, 45, 47, 49, 50, 53, 54, 55, 56, 57]


len(nan_index)

17


budget = [10000000.0, 422000, 9000000.0, 11000000.0, 20000000.0,
          5000000.0, 7000000.0, 15000000.0, 28300000.0, 7500000.0,
          5000000.0, 9000000.0, 5000000.0, 4500000.0, 4500000.0,
          8000000.0, 16000000.0]
print(budget) #showing the budget list

[10000000.0, 422000, 9000000.0, 11000000.0, 20000000.0, 5000000.0, 7000000.0, 15000000.0, 28300000.0, 7500000.0, 5000000.0, 9000000.0, 5000000.0, 4500000.0, 4500000.0, 8000000.0, 16000000.0]


for i,x in enumerate(nan_index):
    demo1_pg.loc[x ,'budget'] = budget[i]


len(demo1_pg)

60


profit_pg = []
for i,x in enumerate(worldwide_pg):
    profit_pg.append(x-demo1_pg.budget[i])
print(profit_pg) #showing the profit_pg list

[4609597.0, 36918287.0, 447351353.0, 70986904.0, 285937718.0, 176601214.0, 33102988.0, 26696000.0, -4565184.0, -34693666.0, 35694916.0, 4344615.0, 6741732.0, 74830111.0, -21454636.0, 10948425.0, -5561265.0, 120587063.0, 34605762.0, 32973297.0, 69137047.0, -2473712.0, 62667874.0, 83269971.0, -9343870.0, -11012232.0, -2974504.0, 120036382.0, 81120329.0, 3835130.0, -12140606.0, 118582776.0, 3101815.0, 48954968.0, -14230040.0, -1744560.0, 5164458.0, 107956187.0, -12180515.0, 31440294.0, 12815212.0, 150297525.0, 21856053.0, 104285432.0, 28716963.0, -13379219.0, -4718768.0, 7423752.0, 108052686.0, 544368315.0, -2331975.0, -14800922.0, 42892670.0, -213211.0, 3943124.0, -2455108.0, -5600000.0, -14294092.0, 71808942.0, 20000000.0]


len(profit_pg)

60


no_tickets_pg = []
for i in worldwide_pg:
    no_tickets_pg.append(round(i/10))
print(no_tickets_pg) #showing the no_tickets_pg list

[970960, 4691829, 54235135, 7398690, 30593772, 21660121, 3810299, 2711800, 53482, 3730633, 4749492, 1934462, 3874173, 11483011, 4354536, 1894842, 343874, 13758706, 6460576, 3347330, 8913705, 852629, 6466787, 10626997, 3565613, 398777, 702550, 15203638, 17112033, 1383513, 1485939, 13458278, 610182, 6395497, 1076996, 3225544, 1516446, 12795619, 281948, 4344029, 1781521, 15729752, 3585605, 11928543, 4071696, 1492078, 328123, 1492375, 12505269, 54936832, 666802, 19908, 6489267, 478679, 844312, 204489, 240000, 170591, 8000894, 4800000]


len(no_tickets_pg)

60


demo1_pg['Worldwide_Gross'] = worldwide_pg
demo1_pg["Foreign_Gross"] = foreign_pg
demo1_pg['Domestic_Gross'] = domestic_pg
demo1_pg["Profit"] = profit_pg
demo1_pg['Tickets'] = no_tickets_pg


demo1_pg.head()


foreign_gross_pgx = []
for i in foreign_pg:
    foreign_gross_pgx.append("${:,.0f}".format(i))
print(foreign_gross_pgx) #showing the foreign_gross_pgx list

['$0', '$0', '$341,200,000', '$6,196,787', '$173,514,909', '$108,500,000', '$3,402,846', '$0', '$0', '$9,510,292', '$6,213,824', '$182,616', '$5,990,639', '$62,500,000', '$0', '$99,995', '$0', '$55,314,621', '$32,941,600', '$16,980', '$26,186,663', '$5,033,288', '$3,962,142', '$23,700,000', '$0', '$0', '$0', '$47,400,000', '$70,200,000', '$3,673,096', '$0', '$91,400,000', '$0', '$41,000,000', '$0', '$0', '$0', '$72,000,000', '$0', '$0', '$0', '$119,610,720', '$0', '$0', '$0', '$0', '$0', '$0', '$3,561', '$330,552,828', '$0', '$0', '$0', '$0', '$0', '$507,770', '$0', '$1,000,000', '$8,942', '$0']


len(foreign_gross_pgx)

60


worldwide_gross_pgx = []
for i in worldwide_pg:
    worldwide_gross_pgx.append("${:,.0f}".format(i))
print(worldwide_gross_pgx) #showing the worldwide_gross_pgx list

['$9,709,597', '$46,918,287', '$542,351,353', '$73,986,904', '$305,937,718', '$216,601,214', '$38,102,988', '$27,118,000', '$534,816', '$37,306,334', '$47,494,916', '$19,344,615', '$38,741,732', '$114,830,111', '$43,545,364', '$18,948,425', '$3,438,735', '$137,587,063', '$64,605,762', '$33,473,297', '$89,137,047', '$8,526,288', '$64,667,874', '$106,269,971', '$35,656,130', '$3,987,768', '$7,025,496', '$152,036,382', '$171,120,329', '$13,835,130', '$14,859,394', '$134,582,776', '$6,101,815', '$63,954,968', '$10,769,960', '$32,255,440', '$15,164,458', '$127,956,187', '$2,819,485', '$43,440,294', '$17,815,212', '$157,297,525', '$35,856,053', '$119,285,432', '$40,716,963', '$14,920,781', '$3,281,232', '$14,923,752', '$125,052,686', '$549,368,315', '$6,668,025', '$199,078', '$64,892,670', '$4,786,789', '$8,443,124', '$2,044,892', '$2,400,000', '$1,705,908', '$80,008,942', '$48,000,000']


len(worldwide_gross_pgx)

60


domestic_gross_pgx = []
for i in domestic_pg:
    domestic_gross_pgx.append("${:,.0f}".format(i))
print(domestic_gross_pgx) #showing the domestic_gross_pgx list

['$0', '$0', '$201,151,353', '$67,790,117', '$132,422,809', '$108,101,214', '$34,700,142', '$0', '$0', '$27,796,042', '$41,281,092', '$19,161,999', '$32,751,093', '$52,330,111', '$0', '$18,848,430', '$0', '$82,272,442', '$31,664,162', '$33,456,317', '$62,950,384', '$3,493,000', '$60,705,732', '$82,569,971', '$0', '$0', '$0', '$104,636,382', '$100,920,329', '$10,162,034', '$0', '$43,182,776', '$0', '$22,954,968', '$0', '$0', '$0', '$55,956,187', '$0', '$0', '$0', '$37,686,805', '$0', '$0', '$0', '$0', '$0', '$0', '$125,049,125', '$218,815,487', '$0', '$0', '$0', '$0', '$0', '$1,537,122', '$0', '$705,908', '$80,000,000', '$0']


len(domestic_gross_pgx)

60


profit_pgx = []
for i in profit_pg:
    profit_pgx.append("${:,.0f}".format(i))
print(profit_pgx) #showing the profit_pgx list

['$4,609,597', '$36,918,287', '$447,351,353', '$70,986,904', '$285,937,718', '$176,601,214', '$33,102,988', '$26,696,000', '$-4,565,184', '$-34,693,666', '$35,694,916', '$4,344,615', '$6,741,732', '$74,830,111', '$-21,454,636', '$10,948,425', '$-5,561,265', '$120,587,063', '$34,605,762', '$32,973,297', '$69,137,047', '$-2,473,712', '$62,667,874', '$83,269,971', '$-9,343,870', '$-11,012,232', '$-2,974,504', '$120,036,382', '$81,120,329', '$3,835,130', '$-12,140,606', '$118,582,776', '$3,101,815', '$48,954,968', '$-14,230,040', '$-1,744,560', '$5,164,458', '$107,956,187', '$-12,180,515', '$31,440,294', '$12,815,212', '$150,297,525', '$21,856,053', '$104,285,432', '$28,716,963', '$-13,379,219', '$-4,718,768', '$7,423,752', '$108,052,686', '$544,368,315', '$-2,331,975', '$-14,800,922', '$42,892,670', '$-213,211', '$3,943,124', '$-2,455,108', '$-5,600,000', '$-14,294,092', '$71,808,942', '$20,000,000']


len(profit_pgx)

60


str_tickets_pgx = []
for i in no_tickets_pg:
    str_tickets_pgx.append("{:,.0f}".format(i))
print(str_tickets_pgx) #showing the str_tickets_pgx list

['970,960', '4,691,829', '54,235,135', '7,398,690', '30,593,772', '21,660,121', '3,810,299', '2,711,800', '53,482', '3,730,633', '4,749,492', '1,934,462', '3,874,173', '11,483,011', '4,354,536', '1,894,842', '343,874', '13,758,706', '6,460,576', '3,347,330', '8,913,705', '852,629', '6,466,787', '10,626,997', '3,565,613', '398,777', '702,550', '15,203,638', '17,112,033', '1,383,513', '1,485,939', '13,458,278', '610,182', '6,395,497', '1,076,996', '3,225,544', '1,516,446', '12,795,619', '281,948', '4,344,029', '1,781,521', '15,729,752', '3,585,605', '11,928,543', '4,071,696', '1,492,078', '328,123', '1,492,375', '12,505,269', '54,936,832', '666,802', '19,908', '6,489,267', '478,679', '844,312', '204,489', '240,000', '170,591', '8,000,894', '4,800,000']


len(str_tickets_pgx)

60


str_budget_pgx = []
for i in demo1_pg.budget:
    str_budget_pgx.append("${:,.0f}".format(i))
print(str_budget_pgx) #showing the str_budget_pgx list

['$5,100,000', '$10,000,000', '$95,000,000', '$3,000,000', '$20,000,000', '$40,000,000', '$5,000,000', '$422,000', '$5,100,000', '$72,000,000', '$11,800,000', '$15,000,000', '$32,000,000', '$40,000,000', '$65,000,000', '$8,000,000', '$9,000,000', '$17,000,000', '$30,000,000', '$500,000', '$20,000,000', '$11,000,000', '$2,000,000', '$23,000,000', '$45,000,000', '$15,000,000', '$10,000,000', '$32,000,000', '$90,000,000', '$10,000,000', '$27,000,000', '$16,000,000', '$3,000,000', '$15,000,000', '$25,000,000', '$34,000,000', '$10,000,000', '$20,000,000', '$15,000,000', '$12,000,000', '$5,000,000', '$7,000,000', '$14,000,000', '$15,000,000', '$12,000,000', '$28,300,000', '$8,000,000', '$7,500,000', '$17,000,000', '$5,000,000', '$9,000,000', '$15,000,000', '$22,000,000', '$5,000,000', '$4,500,000', '$4,500,000', '$8,000,000', '$16,000,000', '$8,200,000', '$28,000,000']


len(str_budget_pgx)

60


demo1_pg['Worldwide_Gross_x'] = worldwide_gross_pgx
demo1_pg["Foreign_Gross_x"] = foreign_gross_pgx
demo1_pg['Domestic_Gross_x'] = domestic_gross_pgx
demo1_pg["Profit_x"] = profit_pgx
demo1_pg['Tickets_x'] = str_tickets_pgx
demo1_pg['Production_Budget_x'] = str_budget_pgx


demo1_pg.head()


demo1_pg.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 60 entries, 0 to 59
Data columns (total 26 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   movie                60 non-null     object 
 1   rating               60 non-null     object 
 2   genre                60 non-null     object 
 3   year                 60 non-null     int64  
 4   released             60 non-null     object 
 5   score                60 non-null     float64
 6   votes                60 non-null     float64
 7   director             60 non-null     object 
 8   writer               60 non-null     object 
 9   star                 60 non-null     object 
 10  country              60 non-null     object 
 11  budget               60 non-null     float64
 12  gross                60 non-null     float64
 13  company              60 non-null     object 
 14  runtime              60 non-null     float64
 15  Worldwide_Gross      60 non-null     int64  
 16  Foreign_Gross        60 non-null     int64  
 17  Domestic_Gross       60 non-null     int64  
 18  Profit               60 non-null     float64
 19  Tickets              60 non-null     int64  
 20  Worldwide_Gross_x    60 non-null     object 
 21  Foreign_Gross_x      60 non-null     object 
 22  Domestic_Gross_x     60 non-null     object 
 23  Profit_x             60 non-null     object 
 24  Tickets_x            60 non-null     object 
 25  Production_Budget_x  60 non-null     object 
dtypes: float64(6), int64(5), object(15)
memory usage: 12.3+ KB


Drama_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 154 entries, 0 to 153
Data columns (total 23 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   Movie                154 non-null    object 
 1   Release_Date         154 non-null    object 
 2   Genre                154 non-null    object 
 3   Rating               154 non-null    object 
 4   Production_Budget    154 non-null    int64  
 5   Production_Budget_x  154 non-null    object 
 6   Domestic_Gross       154 non-null    int64  
 7   Domestic_Gross_x     154 non-null    object 
 8   Foreign_Gross        127 non-null    float64
 9   Foreign_Gross_x      127 non-null    object 
 10  Worldwide_Gross      154 non-null    object 
 11  Worldwide_Gross_x    154 non-null    int64  
 12  Profit               154 non-null    int64  
 13  Profit_x             154 non-null    object 
 14  Tickets              154 non-null    int64  
 15  Tickets_x            154 non-null    object 
 16  Runtime              153 non-null    float64
 17  Averagerating        154 non-null    float64
 18  Company              153 non-null    object 
 19  Studio               154 non-null    object 
 20  Star                 154 non-null    object 
 21  Director             154 non-null    object 
 22  Writer               154 non-null    object 
dtypes: float64(3), int64(5), object(15)
memory usage: 27.8+ KB


demo1_pg = demo1_pg.drop(['year',  'votes', 'country', 'gross'], axis=1)


demo1_pg.head()


demo1_pg.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 60 entries, 0 to 59
Data columns (total 22 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   movie                60 non-null     object 
 1   rating               60 non-null     object 
 2   genre                60 non-null     object 
 3   released             60 non-null     object 
 4   score                60 non-null     float64
 5   director             60 non-null     object 
 6   writer               60 non-null     object 
 7   star                 60 non-null     object 
 8   budget               60 non-null     float64
 9   company              60 non-null     object 
 10  runtime              60 non-null     float64
 11  Worldwide_Gross      60 non-null     int64  
 12  Foreign_Gross        60 non-null     int64  
 13  Domestic_Gross       60 non-null     int64  
 14  Profit               60 non-null     float64
 15  Tickets              60 non-null     int64  
 16  Worldwide_Gross_x    60 non-null     object 
 17  Foreign_Gross_x      60 non-null     object 
 18  Domestic_Gross_x     60 non-null     object 
 19  Profit_x             60 non-null     object 
 20  Tickets_x            60 non-null     object 
 21  Production_Budget_x  60 non-null     object 
dtypes: float64(4), int64(4), object(14)
memory usage: 10.4+ KB


demo1_pg = demo1_pg[['movie','released','genre','rating','budget','Production_Budget_x',
           'Domestic_Gross','Domestic_Gross_x','Foreign_Gross','Foreign_Gross_x','Worldwide_Gross',
           'Worldwide_Gross_x','Profit','Profit_x','Tickets','Tickets_x','runtime','score',
           'company','star','director','writer']]


demo1_pg.head()


demo1_pg.columns = ['Movie','Release_Date','Genre','Rating','Production_Budget','Production_Budget_x',
           'Domestic_Gross','Domestic_Gross_x','Foreign_Gross','Foreign_Gross_x','Worldwide_Gross',
           'Worldwide_Gross_x','Profit','Profit_x','Tickets','Tickets_x','Runtime','Averagerating',
            'Company','Star','Director','Writer']


demo1_pg.head()


Drama_df = Drama_df.drop(['Studio'], axis=1)


Drama_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 154 entries, 0 to 153
Data columns (total 22 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   Movie                154 non-null    object 
 1   Release_Date         154 non-null    object 
 2   Genre                154 non-null    object 
 3   Rating               154 non-null    object 
 4   Production_Budget    154 non-null    int64  
 5   Production_Budget_x  154 non-null    object 
 6   Domestic_Gross       154 non-null    int64  
 7   Domestic_Gross_x     154 non-null    object 
 8   Foreign_Gross        127 non-null    float64
 9   Foreign_Gross_x      127 non-null    object 
 10  Worldwide_Gross      154 non-null    object 
 11  Worldwide_Gross_x    154 non-null    int64  
 12  Profit               154 non-null    int64  
 13  Profit_x             154 non-null    object 
 14  Tickets              154 non-null    int64  
 15  Tickets_x            154 non-null    object 
 16  Runtime              153 non-null    float64
 17  Averagerating        154 non-null    float64
 18  Company              153 non-null    object 
 19  Star                 154 non-null    object 
 20  Director             154 non-null    object 
 21  Writer               154 non-null    object 
dtypes: float64(3), int64(5), object(14)
memory usage: 26.6+ KB


demo1_pg.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 60 entries, 0 to 59
Data columns (total 22 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   Movie                60 non-null     object 
 1   Release_Date         60 non-null     object 
 2   Genre                60 non-null     object 
 3   Rating               60 non-null     object 
 4   Production_Budget    60 non-null     float64
 5   Production_Budget_x  60 non-null     object 
 6   Domestic_Gross       60 non-null     int64  
 7   Domestic_Gross_x     60 non-null     object 
 8   Foreign_Gross        60 non-null     int64  
 9   Foreign_Gross_x      60 non-null     object 
 10  Worldwide_Gross      60 non-null     int64  
 11  Worldwide_Gross_x    60 non-null     object 
 12  Profit               60 non-null     float64
 13  Profit_x             60 non-null     object 
 14  Tickets              60 non-null     int64  
 15  Tickets_x            60 non-null     object 
 16  Runtime              60 non-null     float64
 17  Averagerating        60 non-null     float64
 18  Company              60 non-null     object 
 19  Star                 60 non-null     object 
 20  Director             60 non-null     object 
 21  Writer               60 non-null     object 
dtypes: float64(4), int64(4), object(14)
memory usage: 10.4+ KB


demo_drama = Drama_df.append(demo1_pg, ignore_index=True)

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\1081320491.py:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  demo_drama = Drama_df.append(demo1_pg, ignore_index=True)


demo_drama


demo_rest = demo_nc.append(demo_g, ignore_index=True).append(demo_r, ignore_index=True)

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\1901008892.py:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  demo_rest = demo_nc.append(demo_g, ignore_index=True).append(demo_r, ignore_index=True)


demo_rest.head()


demo_rest = demo_rest.drop(labels=[12,16,19,23,27], axis=0)
demo_rest = demo_rest.reset_index(drop=True)


demo_rest.head()


demo_rest = demo_rest.fillna(0)


demo_rest.head()


nan_index = []
for i,x in enumerate(demo_rest.budget):
    if x == 0.0 :nan_index.append(i)
print(nan_index) #showing the nan_index list

[0, 1, 2, 3, 7, 9, 12, 13, 14, 15, 16, 18, 22, 23, 24, 26, 29, 30]


len(nan_index)

18


budget = [12500000, 1000000, 20000, 955472, 5000000, 2734384,
         4000000, 35446775, 700000, 8600000, 7000000, 4400000,
         8500000, 20000000, 100000, 6500000, 11500000, 9000000]
print(budget) #showing the budget list

[12500000, 1000000, 20000, 955472, 5000000, 2734384, 4000000, 35446775, 700000, 8600000, 7000000, 4400000, 8500000, 20000000, 100000, 6500000, 11500000, 9000000]


for i,x in enumerate(nan_index):
    demo_rest.loc[x ,'budget'] = budget[i]


demo_rest.head()


worldwide_rest = [17356268, 1008404, 277845, 1614784, 20412216, 20350754, 98410061, 496059,
                 15121165, 1022148, 67091915, 20412841, 19465835, 195494, 2411143,
                 1025228, 18587135, 8721243, 40300, 10015449, 80693537,
                 54766923, 77211836, 34718173, 1951683, 636796, 2447576, 9171289, 
                 3256082, 13000000, 11000000]
print(worldwide_rest) #showing the worldwide_rest list

[17356268, 1008404, 277845, 1614784, 20412216, 20350754, 98410061, 496059, 15121165, 1022148, 67091915, 20412841, 19465835, 195494, 2411143, 1025228, 18587135, 8721243, 40300, 10015449, 80693537, 54766923, 77211836, 34718173, 1951683, 636796, 2447576, 9171289, 3256082, 13000000, 11000000]


len(worldwide_rest)

31


domestic_rest = [12594698, 0, 0, 0, 7412216, 0, 54580300, 0, 2532228, 71616, 4604982,  
                 4002293, 2199787, 0, 0, 0, 0, 0, 0, 0, 75600072, 0, 22455510, 23438250, 
                 1596371, 0, 0, 0, 0, 0, 0]
print(domestic_rest) #showing the domestic_rest list

[12594698, 0, 0, 0, 7412216, 0, 54580300, 0, 2532228, 71616, 4604982, 4002293, 2199787, 0, 0, 0, 0, 0, 0, 0, 75600072, 0, 22455510, 23438250, 1596371, 0, 0, 0, 0, 0, 0]


len(domestic_rest)

31


foreign_rest = []
for i,x in enumerate(worldwide_rest):
    if domestic_rest[i] == 0:foreign_rest.append(0)
    else:foreign_rest.append(x-domestic_rest[i])
print(foreign_rest) #showing the foreign_rest list

[4761570, 0, 0, 0, 13000000, 0, 43829761, 0, 12588937, 950532, 62486933, 16410548, 17266048, 0, 0, 0, 0, 0, 0, 0, 5093465, 0, 54756326, 11279923, 355312, 0, 0, 0, 0, 0, 0]


len(foreign_rest)

31


profit_rest = []
for i,x in enumerate(worldwide_rest):
    profit_rest.append(x-demo_rest.budget[i])
print(profit_rest) #showing the profit_rest list

[4856268.0, 8404.0, 257845.0, 659312.0, 18912216.0, -24649246.0, 89410061.0, -4503941.0, 121165.0, -1712236.0, 52091915.0, 13912841.0, 15465835.0, -35251281.0, 1711143.0, -7574772.0, 11587135.0, -9278757.0, -4359700.0, -6984551.0, 58693537.0, 48766923.0, 68711836.0, 14718173.0, 1851683.0, -25363204.0, -4052424.0, -12828711.0, 556082.0, 1500000.0, 2000000.0]


len(profit_rest)

31


no_tickets_rest = []
for i in worldwide_rest:
    no_tickets_rest.append(round(i/10))
print(no_tickets_rest) #showing the no_tickets_rest list

[1735627, 100840, 27784, 161478, 2041222, 2035075, 9841006, 49606, 1512116, 102215, 6709192, 2041284, 1946584, 19549, 241114, 102523, 1858714, 872124, 4030, 1001545, 8069354, 5476692, 7721184, 3471817, 195168, 63680, 244758, 917129, 325608, 1300000, 1100000]


len(no_tickets_rest)

31


worldwide_gross_restx = []
for i in worldwide_rest:
    worldwide_gross_restx.append("${:,.0f}".format(i))
print(worldwide_gross_restx) #showing the worldwide_gross_restx list

['$17,356,268', '$1,008,404', '$277,845', '$1,614,784', '$20,412,216', '$20,350,754', '$98,410,061', '$496,059', '$15,121,165', '$1,022,148', '$67,091,915', '$20,412,841', '$19,465,835', '$195,494', '$2,411,143', '$1,025,228', '$18,587,135', '$8,721,243', '$40,300', '$10,015,449', '$80,693,537', '$54,766,923', '$77,211,836', '$34,718,173', '$1,951,683', '$636,796', '$2,447,576', '$9,171,289', '$3,256,082', '$13,000,000', '$11,000,000']


len(worldwide_gross_restx)

31


domestic_gross_restx = []
for i in domestic_rest:
    domestic_gross_restx.append("${:,.0f}".format(i))
print(domestic_gross_restx) #showing the domestic_gross_restx list

['$12,594,698', '$0', '$0', '$0', '$7,412,216', '$0', '$54,580,300', '$0', '$2,532,228', '$71,616', '$4,604,982', '$4,002,293', '$2,199,787', '$0', '$0', '$0', '$0', '$0', '$0', '$0', '$75,600,072', '$0', '$22,455,510', '$23,438,250', '$1,596,371', '$0', '$0', '$0', '$0', '$0', '$0']


len(domestic_gross_restx)

31


foreign_gross_restx = []
for i in foreign_rest:
    foreign_gross_restx.append("${:,.0f}".format(i))
print(foreign_gross_restx) #showing the foreign_gross_restx list

['$4,761,570', '$0', '$0', '$0', '$13,000,000', '$0', '$43,829,761', '$0', '$12,588,937', '$950,532', '$62,486,933', '$16,410,548', '$17,266,048', '$0', '$0', '$0', '$0', '$0', '$0', '$0', '$5,093,465', '$0', '$54,756,326', '$11,279,923', '$355,312', '$0', '$0', '$0', '$0', '$0', '$0']


len(foreign_gross_restx)

31


profit_restx = []
for i in profit_rest:
    profit_restx.append("${:,.0f}".format(i))
print(profit_restx) #showing the profit_restx list

['$4,856,268', '$8,404', '$257,845', '$659,312', '$18,912,216', '$-24,649,246', '$89,410,061', '$-4,503,941', '$121,165', '$-1,712,236', '$52,091,915', '$13,912,841', '$15,465,835', '$-35,251,281', '$1,711,143', '$-7,574,772', '$11,587,135', '$-9,278,757', '$-4,359,700', '$-6,984,551', '$58,693,537', '$48,766,923', '$68,711,836', '$14,718,173', '$1,851,683', '$-25,363,204', '$-4,052,424', '$-12,828,711', '$556,082', '$1,500,000', '$2,000,000']


len(profit_restx)

31


str_tickets_restx = []
for i in no_tickets_rest:
    str_tickets_restx.append("{:,.0f}".format(i))
print(str_tickets_restx) #showing the str_tickets_restx list

['1,735,627', '100,840', '27,784', '161,478', '2,041,222', '2,035,075', '9,841,006', '49,606', '1,512,116', '102,215', '6,709,192', '2,041,284', '1,946,584', '19,549', '241,114', '102,523', '1,858,714', '872,124', '4,030', '1,001,545', '8,069,354', '5,476,692', '7,721,184', '3,471,817', '195,168', '63,680', '244,758', '917,129', '325,608', '1,300,000', '1,100,000']


len(str_tickets_restx)

31


str_budget_restx = []
for i in demo_rest.budget:
    str_budget_restx.append("${:,.0f}".format(i))
print(str_budget_restx) #showing the str_budget_restx list

['$12,500,000', '$1,000,000', '$20,000', '$955,472', '$1,500,000', '$45,000,000', '$9,000,000', '$5,000,000', '$15,000,000', '$2,734,384', '$15,000,000', '$6,500,000', '$4,000,000', '$35,446,775', '$700,000', '$8,600,000', '$7,000,000', '$18,000,000', '$4,400,000', '$17,000,000', '$22,000,000', '$6,000,000', '$8,500,000', '$20,000,000', '$100,000', '$26,000,000', '$6,500,000', '$22,000,000', '$2,700,000', '$11,500,000', '$9,000,000']


len(str_budget_restx)

31


demo_rest = demo_rest.drop(['year',  'votes', 'country', 'gross'], axis=1)


demo_rest['Worldwide_Gross'] = worldwide_rest
demo_rest["Foreign_Gross"] = foreign_rest
demo_rest['Domestic_Gross'] = domestic_rest
demo_rest["Profit"] = profit_rest
demo_rest['Tickets'] = no_tickets_rest

demo_rest['Worldwide_Gross_x'] = worldwide_gross_restx
demo_rest["Foreign_Gross_x"] = foreign_gross_restx
demo_rest['Domestic_Gross_x'] = domestic_gross_restx
demo_rest["Profit_x"] = profit_restx
demo_rest['Tickets_x'] = str_tickets_restx
demo_rest['Production_Budget_x'] = str_budget_restx


demo_rest = demo_rest[['movie','released','genre','rating','budget','Production_Budget_x',
           'Domestic_Gross','Domestic_Gross_x','Foreign_Gross','Foreign_Gross_x','Worldwide_Gross',
           'Worldwide_Gross_x','Profit','Profit_x','Tickets','Tickets_x','runtime','score',
           'company','star','director','writer']]


demo_rest.head()


demo_rest.columns = ['Movie','Release_Date','Genre','Rating','Production_Budget','Production_Budget_x',
           'Domestic_Gross','Domestic_Gross_x','Foreign_Gross','Foreign_Gross_x','Worldwide_Gross',
           'Worldwide_Gross_x','Profit','Profit_x','Tickets','Tickets_x','Runtime','Averagerating',
            'Company','Star','Director','Writer']


demo_rest.head()


demo_drama.head()


Drama_DataFrame = demo_drama.append(demo_rest, ignore_index=True)

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\3808589794.py:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  Drama_DataFrame = demo_drama.append(demo_rest, ignore_index=True)


Drama_DataFrame = Drama_DataFrame[['Movie','Release_Date','Genre','Rating','Production_Budget','Production_Budget_x',
           'Domestic_Gross','Domestic_Gross_x','Foreign_Gross','Foreign_Gross_x','Worldwide_Gross_x',
           'Worldwide_Gross','Profit','Profit_x','Tickets','Tickets_x','Runtime','Averagerating',
            'Company','Star','Director','Writer']]


Drama_DataFrame.columns = ['Movie','Release_Date','Genre','Rating','Production_Budget','Production_Budget_x',
           'Domestic_Gross','Domestic_Gross_x','Foreign_Gross','Foreign_Gross_x','Worldwide_Gross',
           'Worldwide_Gross_x','Profit','Profit_x','Tickets','Tickets_x','Runtime','Averagerating',
            'Company','Star','Director','Writer']


Drama_DataFrame.head()


g_name  = ['Beauty and the Beast 1991' , 'The Little Rascals', 'Ramona and Beezus', 
           'The Black Stallion', 'The Hunchback of Notre Drame', 'Babe', 'Pollyanna',
           'Babe: Pig in the City', 'Lassie Come Home', 'Charlotte\'s Web', 'A Little Princess',
           'Kit Kittredge: An American Girl', 'The Rookie', 'The Secret Garden', 'The Sound of Music',
           'The Tale of Despereaux', 'The Lion King 1994', 'Bambi 1942', 'My Fair Lady 1964', 
           'Before the Wrath', 'Hachiko: A Dog\'s Story', 'Giant', 'The Ten Commandments 1966',
           'The Quiet Man', 'Three Cions in the Fountain', 'Miracle of Marcelino']


print(g_name)

['Beauty and the Beast 1991', 'The Little Rascals', 'Ramona and Beezus', 'The Black Stallion', 'The Hunchback of Notre Drame', 'Babe', 'Pollyanna', 'Babe: Pig in the City', 'Lassie Come Home', "Charlotte's Web", 'A Little Princess', 'Kit Kittredge: An American Girl', 'The Rookie', 'The Secret Garden', 'The Sound of Music', 'The Tale of Despereaux', 'The Lion King 1994', 'Bambi 1942', 'My Fair Lady 1964', 'Before the Wrath', "Hachiko: A Dog's Story", 'Giant', 'The Ten Commandments 1966', 'The Quiet Man', 'Three Cions in the Fountain', 'Miracle of Marcelino']


len(g_name)

26


g_writer = ['Linda Woolverton','Penelope Spheeris','Beverly Cleary','Melissa Mathison','Victor Hugo',
            'Chris Noonan','Eleanor Hodgman Porter','Judy Morris','Eric Knight','E. B. White',
            'Frances Hodgson Burnett','Valerie Tripp','Mike Rich','Caroline Thompson','Ernest Lehman',
            'Kate DiCamillo','Jonathan Roberts','Perce Pearce','Alan Jay Lerner','Brent Miller Jr.',
            'Stephen P. Lindsey','Edna Ferber',' Fredric M. Frank','Frank S. Nugent','John Patrick',
            'José María Sánchez-Silva']


print(g_writer)

['Linda Woolverton', 'Penelope Spheeris', 'Beverly Cleary', 'Melissa Mathison', 'Victor Hugo', 'Chris Noonan', 'Eleanor Hodgman Porter', 'Judy Morris', 'Eric Knight', 'E. B. White', 'Frances Hodgson Burnett', 'Valerie Tripp', 'Mike Rich', 'Caroline Thompson', 'Ernest Lehman', 'Kate DiCamillo', 'Jonathan Roberts', 'Perce Pearce', 'Alan Jay Lerner', 'Brent Miller Jr.', 'Stephen P. Lindsey', 'Edna Ferber', ' Fredric M. Frank', 'Frank S. Nugent', 'John Patrick', 'José María Sánchez-Silva']


len(g_writer)

26


g_date = ['Novemeber 22, 1991', 'August 5, 1994', 'July 23, 2010', 'October 17, 1979', 'June 21, 1996',
         'August 4, 1995', 'May 19, 1960', 'November 25, 1998', 'December 1943', 'October 15, 1952',
         'May 10, 1995', 'July 2, 2008', 'March 29, 2002', 'April 13 1993', 'April 1, 1993',
         'December 19, 2008', 'June 24, 1994', 'August 21, 1942', 'December 25, 1964', 'March 3, 2020',
         'March 12, 2010', 'Novemebr 24, 1952', 'October 5, 1956', 'Septemebr 14, 1954', 'May 15, 1954',
         'October 22, 1956']


print(g_date)

['Novemeber 22, 1991', 'August 5, 1994', 'July 23, 2010', 'October 17, 1979', 'June 21, 1996', 'August 4, 1995', 'May 19, 1960', 'November 25, 1998', 'December 1943', 'October 15, 1952', 'May 10, 1995', 'July 2, 2008', 'March 29, 2002', 'April 13 1993', 'April 1, 1993', 'December 19, 2008', 'June 24, 1994', 'August 21, 1942', 'December 25, 1964', 'March 3, 2020', 'March 12, 2010', 'Novemebr 24, 1952', 'October 5, 1956', 'Septemebr 14, 1954', 'May 15, 1954', 'October 22, 1956']


len(g_date)

26


g_budget = [20000000, 23000000, 15000000, 2700000, 70000000, 30000000, 2500000, 90000000, 666000, 85000000,
           17000000, 10000000, 22000000, 18000000, 8200000, 60000000, 45000000, 858000, 17000000, 300000, 
           10000000, 6400000, 13000000, 1750000, 1700000, 3000000]


print(g_budget)

[20000000, 23000000, 15000000, 2700000, 70000000, 30000000, 2500000, 90000000, 666000, 85000000, 17000000, 10000000, 22000000, 18000000, 8200000, 60000000, 45000000, 858000, 17000000, 300000, 10000000, 6400000, 13000000, 1750000, 1700000, 3000000]


len(g_budget)

26


g_domestic =[206333165, 51764950, 25167002, 0, 100138851, 63658910, 0, 18319860, 0, 82985708, 0, 0, 
            75600072, 0, 163214286, 50877145, 421785283, 102797000, 72000000, 0, 0, 30176619, 0, 7600000,
            5000000, 0]


print(g_domestic)

[206333165, 51764950, 25167002, 0, 100138851, 63658910, 0, 18319860, 0, 82985708, 0, 0, 75600072, 0, 163214286, 50877145, 421785283, 102797000, 72000000, 0, 0, 30176619, 0, 7600000, 5000000, 0]


len(g_domestic)

26


g_foreign = [232323678, 15183000, 1302619, 0, 225361149, 182441090, 0, 50812000, 0, 61000000, 0,
                  0, 4891444, 0, 122999909, 39605172, 564429585, 165203000, 71636, 0, 0, 15790, 0, 377,
                  7000000, 0]


print(g_foreign)

[232323678, 15183000, 1302619, 0, 225361149, 182441090, 0, 50812000, 0, 61000000, 0, 0, 4891444, 0, 122999909, 39605172, 564429585, 165203000, 71636, 0, 0, 15790, 0, 377, 7000000, 0]


len(g_foreign)

26


g_worldwide = [438656843, 66947950, 27469621, 37799643, 325500000, 246100000, 3750000, 69131860,
               4517000, 143985708, 10015449, 17657973, 80491516, 311281000, 286214195, 90482317, 986214868,
              268000000, 72071636, 108998, 47707417, 30194409, 65500000, 7600377, 12000000, 592861]


print(g_worldwide)

[438656843, 66947950, 27469621, 37799643, 325500000, 246100000, 3750000, 69131860, 4517000, 143985708, 10015449, 17657973, 80491516, 311281000, 286214195, 90482317, 986214868, 268000000, 72071636, 108998, 47707417, 30194409, 65500000, 7600377, 12000000, 592861]


len(g_worldwide)

26


g_runtime = [84, 83, 103, 118, 91, 91, 134, 90, 89, 97, 97, 105, 128, 101, 174, 87, 87, 70, 175, 84, 90,
            200, 220, 129, 102, 91]


print(g_runtime)

[84, 83, 103, 118, 91, 91, 134, 90, 89, 97, 97, 105, 128, 101, 174, 87, 87, 70, 175, 84, 90, 200, 220, 129, 102, 91]


len(g_runtime)

26


g_rating = [8.0, 6.3, 6.5, 7.4, 7.0, 9.6, 9.0, 5.8, 7.1, 6.3, 7.6, 6.5, 6.9, 7.3, 8.1, 6.1, 8.5, 7.3, 7.8,
           6.6, 8.1, 7.6, 7.9, 7.7, 6.3, 7.1]


print(g_rating)

[8.0, 6.3, 6.5, 7.4, 7.0, 9.6, 9.0, 5.8, 7.1, 6.3, 7.6, 6.5, 6.9, 7.3, 8.1, 6.1, 8.5, 7.3, 7.8, 6.6, 8.1, 7.6, 7.9, 7.7, 6.3, 7.1]


len(g_rating)

26


g_company = ['The Walt Disney Company','Universal Pictures', 'Fox 2000 Pictures', 'Omni Zoetrope', 
             'The Walt Disney Company', 'Universal Pictures', 'The Walt Disney Company', 
             'Universal Pictures', 'Metro-Goldwyn-Mayer', 'Hanna-Barber-Productions', 
             'Warner Bros. Pictures', 'Picturehouse', 'The Walt Disney Company', 'American Zoetrope',
             '20th Century Studios', 'Universal Pictures', 'The Walt Disney Company', 
             'The Walt Disney Company', 'Warner Bros. Pictures', 'NaN', 'Inferno Distribution',
             'Warner Bros. Pictures', 'Motion Picture Associates', 'Republic Pictures', 
             '20th Century Studios', 'United Motion Pictures']


print(g_company)

['The Walt Disney Company', 'Universal Pictures', 'Fox 2000 Pictures', 'Omni Zoetrope', 'The Walt Disney Company', 'Universal Pictures', 'The Walt Disney Company', 'Universal Pictures', 'Metro-Goldwyn-Mayer', 'Hanna-Barber-Productions', 'Warner Bros. Pictures', 'Picturehouse', 'The Walt Disney Company', 'American Zoetrope', '20th Century Studios', 'Universal Pictures', 'The Walt Disney Company', 'The Walt Disney Company', 'Warner Bros. Pictures', 'NaN', 'Inferno Distribution', 'Warner Bros. Pictures', 'Motion Picture Associates', 'Republic Pictures', '20th Century Studios', 'United Motion Pictures']


len(g_company)

26


g_director = ['Gary Trousdale', 'Penelope Spheeris', 'Elizabeth Allen Ressenbaum', 'Carral Ballard', 
             'Gary Trouside', 'Chris Noonan', 'David Swift', 'George Miller', 'Fred M. Wilcox',
             'Gary Winick', 'Alfonso Cuaron', 'Patricia Rozema', 'John Lee Hancock', 'Agnieszka Holland', 
             'Robert Wise', 'Sam Fell', 'Rob Minkoff', 'John Hubley', 'Cecil Beaton', 'Brent Miller',
             'Lasse Hallstrom', 'George Stevens', 'Cecil B. Demille', 'John Ford', 'Jean Negulesco',
             'Ladislao Vajda']


print(g_director)

['Gary Trousdale', 'Penelope Spheeris', 'Elizabeth Allen Ressenbaum', 'Carral Ballard', 'Gary Trouside', 'Chris Noonan', 'David Swift', 'George Miller', 'Fred M. Wilcox', 'Gary Winick', 'Alfonso Cuaron', 'Patricia Rozema', 'John Lee Hancock', 'Agnieszka Holland', 'Robert Wise', 'Sam Fell', 'Rob Minkoff', 'John Hubley', 'Cecil Beaton', 'Brent Miller', 'Lasse Hallstrom', 'George Stevens', 'Cecil B. Demille', 'John Ford', 'Jean Negulesco', 'Ladislao Vajda']


len(g_director)

26


g_star  = ['Paige O\'Hara', 'Brittany Ashton', 'Joey King', 'Kelly Reno', 'Demi Moore', 'James Cromwell', 
           'Hayley Mills', 'James Cromwell', 'Roddy McDowall', 'Dokota Fanning', 'Liesel Matthews',
          'Abigail Breslin', 'Dennis Quaid', 'Kate Maberly', 'Julie Andrews', 'Matthew Brodewick', 
          'James Earl Jones', 'Donnie Dunagan', 'Audley Hepburn', 'Gemma Rizzuto', 'Richard Gere',
          'James Dean', 'Yul Brynner', 'John Wayne', 'Jean Peters', 'Pablito Calvo']
len(g_star)

26


print(g_star)

["Paige O'Hara", 'Brittany Ashton', 'Joey King', 'Kelly Reno', 'Demi Moore', 'James Cromwell', 'Hayley Mills', 'James Cromwell', 'Roddy McDowall', 'Dokota Fanning', 'Liesel Matthews', 'Abigail Breslin', 'Dennis Quaid', 'Kate Maberly', 'Julie Andrews', 'Matthew Brodewick', 'James Earl Jones', 'Donnie Dunagan', 'Audley Hepburn', 'Gemma Rizzuto', 'Richard Gere', 'James Dean', 'Yul Brynner', 'John Wayne', 'Jean Peters', 'Pablito Calvo']


g_genre = []
for i in range(26):g_genre.append('Drama')
print(g_genre) #showing the g_genre list

['Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama']


len(g_genre)

26


g_rated = []
for i in range(26):g_rated.append('G')
print(g_rated) #showing the g_rated list

['G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G', 'G']


len(g_rated)

26


g_profit = []
for x,y in enumerate(g_worldwide):
    g_profit.append(y-g_budget[x])
print(g_profit) #showing the g_profit list

[418656843, 43947950, 12469621, 35099643, 255500000, 216100000, 1250000, -20868140, 3851000, 58985708, -6984551, 7657973, 58491516, 293281000, 278014195, 30482317, 941214868, 267142000, 55071636, -191002, 37707417, 23794409, 52500000, 5850377, 10300000, -2407139]


len(g_profit)

26


g_tickets = []
for i in g_worldwide:
    g_tickets.append(round(i/10))
print(g_tickets) #showing the g_tickets list

[43865684, 6694795, 2746962, 3779964, 32550000, 24610000, 375000, 6913186, 451700, 14398571, 1001545, 1765797, 8049152, 31128100, 28621420, 9048232, 98621487, 26800000, 7207164, 10900, 4770742, 3019441, 6550000, 760038, 1200000, 59286]


len(g_tickets)

26


g_budget_x = []
for i in g_budget:
    g_budget_x.append("${:,.0f}".format(i))
print(g_budget_x) #showing the g_budget_x list

['$20,000,000', '$23,000,000', '$15,000,000', '$2,700,000', '$70,000,000', '$30,000,000', '$2,500,000', '$90,000,000', '$666,000', '$85,000,000', '$17,000,000', '$10,000,000', '$22,000,000', '$18,000,000', '$8,200,000', '$60,000,000', '$45,000,000', '$858,000', '$17,000,000', '$300,000', '$10,000,000', '$6,400,000', '$13,000,000', '$1,750,000', '$1,700,000', '$3,000,000']


len(g_budget_x)

26


g_domestic_x = []
for i in g_domestic:
    g_domestic_x.append("${:,.0f}".format(i))
print(g_domestic_x) #showing the g_domestic_x list

['$206,333,165', '$51,764,950', '$25,167,002', '$0', '$100,138,851', '$63,658,910', '$0', '$18,319,860', '$0', '$82,985,708', '$0', '$0', '$75,600,072', '$0', '$163,214,286', '$50,877,145', '$421,785,283', '$102,797,000', '$72,000,000', '$0', '$0', '$30,176,619', '$0', '$7,600,000', '$5,000,000', '$0']


len(g_domestic_x)

26


g_foreign_x = []
for i in g_foreign:
    g_foreign_x.append("${:,.0f}".format(i))
print(g_foreign_x) #showing the g_foreign_x list

['$232,323,678', '$15,183,000', '$1,302,619', '$0', '$225,361,149', '$182,441,090', '$0', '$50,812,000', '$0', '$61,000,000', '$0', '$0', '$4,891,444', '$0', '$122,999,909', '$39,605,172', '$564,429,585', '$165,203,000', '$71,636', '$0', '$0', '$15,790', '$0', '$377', '$7,000,000', '$0']


len(g_foreign_x)

26


g_worldwide_x = []
for i in g_worldwide:
    g_worldwide_x.append("${:,.0f}".format(i))
print(g_worldwide_x) #showing the g_worldwide_x list

['$438,656,843', '$66,947,950', '$27,469,621', '$37,799,643', '$325,500,000', '$246,100,000', '$3,750,000', '$69,131,860', '$4,517,000', '$143,985,708', '$10,015,449', '$17,657,973', '$80,491,516', '$311,281,000', '$286,214,195', '$90,482,317', '$986,214,868', '$268,000,000', '$72,071,636', '$108,998', '$47,707,417', '$30,194,409', '$65,500,000', '$7,600,377', '$12,000,000', '$592,861']


len(g_worldwide_x)

26


g_profit_x = []
for i in g_profit:
    g_profit_x.append("${:,.0f}".format(i))
print(g_profit_x) #showing the g_profit_x list

['$418,656,843', '$43,947,950', '$12,469,621', '$35,099,643', '$255,500,000', '$216,100,000', '$1,250,000', '$-20,868,140', '$3,851,000', '$58,985,708', '$-6,984,551', '$7,657,973', '$58,491,516', '$293,281,000', '$278,014,195', '$30,482,317', '$941,214,868', '$267,142,000', '$55,071,636', '$-191,002', '$37,707,417', '$23,794,409', '$52,500,000', '$5,850,377', '$10,300,000', '$-2,407,139']


len(g_profit_x)

26


g_tickets_x = []
for i in g_tickets:
    g_tickets_x.append("{:,.0f}".format(i))
print(g_tickets_x) #showing the g_tickets_x list

['43,865,684', '6,694,795', '2,746,962', '3,779,964', '32,550,000', '24,610,000', '375,000', '6,913,186', '451,700', '14,398,571', '1,001,545', '1,765,797', '8,049,152', '31,128,100', '28,621,420', '9,048,232', '98,621,487', '26,800,000', '7,207,164', '10,900', '4,770,742', '3,019,441', '6,550,000', '760,038', '1,200,000', '59,286']


len(g_tickets_x)

26


g_dataframe =  pd.DataFrame({"Movie":g_name, "Release_Date":g_date, "Genre":g_genre, "Rating":g_rated, 
                            "Production_Budget":g_budget, "Production_Budget_x":g_budget_x, 
                            "Domestic_Gross":g_domestic, "Domestic_Gross_x":g_domestic_x, 
                            "Foreign_Gross":g_foreign, "Foreign_Gross_x":g_foreign_x, 
                            "Worldwide_Gross":g_worldwide, "Worldwide_Gross_x":g_worldwide_x, 
                            "Profit":g_profit, "Profit_x":g_profit_x, "Tickets":g_tickets, 
                            "Tickets_x":g_tickets_x, "Runtime":g_runtime, "Averagerating":g_rating, 
                            "Company":g_company, "Star":g_star, "Director":g_director, "Writer":g_writer
                             })


g_dataframe.head()


Drama_DataFrame = Drama_DataFrame.append(g_dataframe, ignore_index=True)

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\3157750573.py:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  Drama_DataFrame = Drama_DataFrame.append(g_dataframe, ignore_index=True)


nc17_name = ['Showgirls', 'The Dreamers', 'Shame', 'Blue Is the Warmest Colour', 'Blue Valentine',
            'Two Girls and a Guy', 'Elles', 'Hell', 'Killer Joe', 'Se, jie', 'Queen of Hearts', 
            'The Evil Dead', 'Man Bites Dog', 'Shame', 'Nymphomaniac: Vol. I', 'Arabian Nights',
            'Frontier(s)', 'Chained', 'Natural Born Killers', 'Clerks', 'Bad Lieutenant', 
            'The Big Feast', 'Beyond the Valley of the Dolls', 'Kids', 'Crash', 'Last Tango in Paris',
            'Pink Flamingos', 'Lust, Caution ', 'Happiness 1998', 'Orgazmo', 'A Dirty Shame', 
            'Young Adam', 'Whore 1991', 'Ma Mère', 'Law of Desire' ]
print(nc17_name) #showing the nc17_name list

['Showgirls', 'The Dreamers', 'Shame', 'Blue Is the Warmest Colour', 'Blue Valentine', 'Two Girls and a Guy', 'Elles', 'Hell', 'Killer Joe', 'Se, jie', 'Queen of Hearts', 'The Evil Dead', 'Man Bites Dog', 'Shame', 'Nymphomaniac: Vol. I', 'Arabian Nights', 'Frontier(s)', 'Chained', 'Natural Born Killers', 'Clerks', 'Bad Lieutenant', 'The Big Feast', 'Beyond the Valley of the Dolls', 'Kids', 'Crash', 'Last Tango in Paris', 'Pink Flamingos', 'Lust, Caution ', 'Happiness 1998', 'Orgazmo', 'A Dirty Shame', 'Young Adam', 'Whore 1991', 'Ma Mère', 'Law of Desire']


len(nc17_name)

35


nc17_director = ['Paul Verhoeven', 'Bernardo Bertolucci', 'Steve McQueen', 'Abdellatif Kechiche', 
                 'Derek Cianfrance', 'James Toback', 'Małgośka Szumowska', 'Tim Fehlbaum', 
                 'William Friedkin','Ang Lee', 'May el-Toukhy', 'Sam Raimi', 'Rémy Belvaux', 
                 'Steve McQueen', 'Lars von Trier', 'Pier Paolo Pasolini', 'Xavier Gens',
                 'Jennifer Lynch', 'Oliver Stone', 'Kevin Smith','Abel Ferrara','John Gulager',
                 'Russ Meyer', 'Larry Clark', 'Paul Haggis', 'Bernardo Bertolucci','John Waters',
                 'Ang Lee', 'Todd Solondz',  'Trey Parker', 'John Waters', 'David Mackenzie',
                 'Ken Russell', 'Christophe Honoré', 'Pedro Almodóvar']
print(nc17_director) #showing the nc17_director list

['Paul Verhoeven', 'Bernardo Bertolucci', 'Steve McQueen', 'Abdellatif Kechiche', 'Derek Cianfrance', 'James Toback', 'Małgośka Szumowska', 'Tim Fehlbaum', 'William Friedkin', 'Ang Lee', 'May el-Toukhy', 'Sam Raimi', 'Rémy Belvaux', 'Steve McQueen', 'Lars von Trier', 'Pier Paolo Pasolini', 'Xavier Gens', 'Jennifer Lynch', 'Oliver Stone', 'Kevin Smith', 'Abel Ferrara', 'John Gulager', 'Russ Meyer', 'Larry Clark', 'Paul Haggis', 'Bernardo Bertolucci', 'John Waters', 'Ang Lee', 'Todd Solondz', 'Trey Parker', 'John Waters', 'David Mackenzie', 'Ken Russell', 'Christophe Honoré', 'Pedro Almodóvar']


len(nc17_director)

35


nc17_writer = ['Joe Eszterhas', 'Gilbert Adair', 'Abi Morgan', 'Ghalia Lacroix', 'Cami Delavigne', 
               'James Toback', 'Tine Byrckel', 'Tim Fehlbaum', 'Tracy Letts', 'Hui-Ling Wang', 
               'Maren Louise Käehne', 'Sam Raimi', 'André Bonzel', 'Abi Morgan', 'Lars von Trier',
               'Dacia Maraini', 'Xavier Gens', 'Jennifer Lynch', 'Oliver Stone', 'Kevin Smith', 
               'Abel Ferrara', 'Patrick Melton', 'Roger Ebert', 'Harmony Korine', 'Paul Haggis', 
               'Franco Arcalli', 'John Waters', 'Hui-Ling Wang', 'Todd Solondz', 'Trey Parker', 
               'John Waters', '	David Mackenzie', 'Deborah Dalton', 'Christophe Honoré',
               'Pedro Almodóvar']
print(nc17_writer) #showing the nc17_writer list

['Joe Eszterhas', 'Gilbert Adair', 'Abi Morgan', 'Ghalia Lacroix', 'Cami Delavigne', 'James Toback', 'Tine Byrckel', 'Tim Fehlbaum', 'Tracy Letts', 'Hui-Ling Wang', 'Maren Louise Käehne', 'Sam Raimi', 'André Bonzel', 'Abi Morgan', 'Lars von Trier', 'Dacia Maraini', 'Xavier Gens', 'Jennifer Lynch', 'Oliver Stone', 'Kevin Smith', 'Abel Ferrara', 'Patrick Melton', 'Roger Ebert', 'Harmony Korine', 'Paul Haggis', 'Franco Arcalli', 'John Waters', 'Hui-Ling Wang', 'Todd Solondz', 'Trey Parker', 'John Waters', '\tDavid Mackenzie', 'Deborah Dalton', 'Christophe Honoré', 'Pedro Almodóvar']


len(nc17_writer)

35


nc17_date = ['September 22, 1995', 'February 6, 2004', 'December 2, 2011', 'October 25, 2013', 
             'December 29, 2010', 'September 9, 1997', 'April 27, 2012', '22 September 2011', 
             'July 27, 2012', 'September 28, 2007', 'November 1, 2019',  'October 15, 1981', 
             '15 January 1993', 'December 2, 2011', 'December 25, 2013',  'July 27, 1980', 'May 9, 2008',
             'August 5, 2012', 'August 26, 1994', 'October 19, 1994', 'November 20, 1992 ',
             'September 22, 2006', 'June 17, 1970', 'July 28, 1995', 'May 6, 2005', 'January 27, 1973',
             'March 17, 1972', 'September 28, 2007', 'October 16, 1998', 'October 23, 1998', 
             'September 24, 2004 ', 'April 16, 2004', 'October 4, 1991', 'May 13, 2005 ', 
             'April 3, 1987']
print(nc17_date) #showing the nc17_date list

['September 22, 1995', 'February 6, 2004', 'December 2, 2011', 'October 25, 2013', 'December 29, 2010', 'September 9, 1997', 'April 27, 2012', '22 September 2011', 'July 27, 2012', 'September 28, 2007', 'November 1, 2019', 'October 15, 1981', '15 January 1993', 'December 2, 2011', 'December 25, 2013', 'July 27, 1980', 'May 9, 2008', 'August 5, 2012', 'August 26, 1994', 'October 19, 1994', 'November 20, 1992 ', 'September 22, 2006', 'June 17, 1970', 'July 28, 1995', 'May 6, 2005', 'January 27, 1973', 'March 17, 1972', 'September 28, 2007', 'October 16, 1998', 'October 23, 1998', 'September 24, 2004 ', 'April 16, 2004', 'October 4, 1991', 'May 13, 2005 ', 'April 3, 1987']


len(nc17_date)

35


nc17_star = ['Elizabeth Berkley', 'Eva Green', 'Michael Fassbender', 'Léa Seydoux', 'Ryan Gosling', 
             'Robert Downey Jr.', 'Juliette Binoche', 'Lisa Vicari', 'Juno Temple', 'Tony Leung Chiu-Wai', 
             'Trine Dyrholm',  'Bruce Campbell', 'Benoît Poelvoorde', 'Michael Fassbender',
             'Charlotte Gainsbourg', 'Ninetto Davoli', 'Karina Testa',  'Vincent D\'Onofrio', 
             'Woody Harrelson', 'Kevin Smith', 'Harvey Keitel', 'Clu Gulager', 'Marcia McBroom', 
             'Leo Fitzpatrick', 'Sandra Bullock', 'Marlon Brando', 'David Lochary', 
             'Tony Leung Chiu-Wai', 'Elizabeth Ashley', 'Michael Dean Jacobs', 'Suzanne Shepherd',
             'Tilda Swinton', 'Theresa Russell', 'Louis Garrel', 'Antonio Banderas']
print(nc17_star) #showing the nc17_star list

['Elizabeth Berkley', 'Eva Green', 'Michael Fassbender', 'Léa Seydoux', 'Ryan Gosling', 'Robert Downey Jr.', 'Juliette Binoche', 'Lisa Vicari', 'Juno Temple', 'Tony Leung Chiu-Wai', 'Trine Dyrholm', 'Bruce Campbell', 'Benoît Poelvoorde', 'Michael Fassbender', 'Charlotte Gainsbourg', 'Ninetto Davoli', 'Karina Testa', "Vincent D'Onofrio", 'Woody Harrelson', 'Kevin Smith', 'Harvey Keitel', 'Clu Gulager', 'Marcia McBroom', 'Leo Fitzpatrick', 'Sandra Bullock', 'Marlon Brando', 'David Lochary', 'Tony Leung Chiu-Wai', 'Elizabeth Ashley', 'Michael Dean Jacobs', 'Suzanne Shepherd', 'Tilda Swinton', 'Theresa Russell', 'Louis Garrel', 'Antonio Banderas']


len(nc17_star)

35


nc17_company = ['Carolco Pictures', 'Recorded Picture Company', 'Film4', 'Wild Bunch', 'Hunting Lane Films',
               'Edward R. Pressman', 'Slot Machine', 'Caligari Film', 'Voltage Pictures', 
               'River Road Entertainment', 'Nordisk Film',  'Renaissance Pictures', 
               'Les Artistes Anonymes', 'Film4', 'Zentropa Entertainments', '	United Artists',
               'BR Films', 'Anchor Bay Entertainment', 'Regency Enterprises', 
               'View Askew Productions', 'Aries Films', 'LivePlanet', '20th Century Fox',
               'Independent Pictures', 'Bob Yari Productions', 'Produzioni Europee', 'Dreamland',
               'River Road Entertainment', 'Killer Films','Avenging Conscience', 'Killer Films',
               'Recorded Picture Company', 'Cheap Date', 'Gemini Films', 'El Deseo']
print(nc17_company) #showing the nc17_company list

['Carolco Pictures', 'Recorded Picture Company', 'Film4', 'Wild Bunch', 'Hunting Lane Films', 'Edward R. Pressman', 'Slot Machine', 'Caligari Film', 'Voltage Pictures', 'River Road Entertainment', 'Nordisk Film', 'Renaissance Pictures', 'Les Artistes Anonymes', 'Film4', 'Zentropa Entertainments', '\tUnited Artists', 'BR Films', 'Anchor Bay Entertainment', 'Regency Enterprises', 'View Askew Productions', 'Aries Films', 'LivePlanet', '20th Century Fox', 'Independent Pictures', 'Bob Yari Productions', 'Produzioni Europee', 'Dreamland', 'River Road Entertainment', 'Killer Films', 'Avenging Conscience', 'Killer Films', 'Recorded Picture Company', 'Cheap Date', 'Gemini Films', 'El Deseo']


len(nc17_company)

35


nc17_budget = [45000000, 15000000, 6500000, 4074940, 1000000, 1000000, 3565572, 12000000, 10000000, 
              15000000, 19000000, 350000, 1000000, 6500000, 4700000, 904765, 3000000,
              700000, 34000000, 230000, 1000000, 3200000, 1000000, 1500000, 6500000,
              1250000, 12000, 15000000, 2200000, 1300000, 15000000, 6400000, 50000, 3259572,
              612072]
print(nc17_budget) #showing the nc17_budget list

[45000000, 15000000, 6500000, 4074940, 1000000, 1000000, 3565572, 12000000, 10000000, 15000000, 19000000, 350000, 1000000, 6500000, 4700000, 904765, 3000000, 700000, 34000000, 230000, 1000000, 3200000, 1000000, 1500000, 6500000, 1250000, 12000, 15000000, 2200000, 1300000, 15000000, 6400000, 50000, 3259572, 612072]


len(nc17_budget)

35


nc17_domestic = [20350754, 2531462, 4002293, 2199787, 9737892, 2057193, 157508, 169705587, 1291645,
                4604982, 0, 2400000, 0, 4002293, 785896, 0, 97182, 0, 50282766, 3073428, 2000022, 
                56131, 0, 7412216, 55334418, 36144824, 0, 4604982, 2746453, 582024, 1339668, 767373,
                0, 71616, 0 ]
print(nc17_domestic) #showing the nc17_domestic list

[20350754, 2531462, 4002293, 2199787, 9737892, 2057193, 157508, 169705587, 1291645, 4604982, 0, 2400000, 0, 4002293, 785896, 0, 97182, 0, 50282766, 3073428, 2000022, 56131, 0, 7412216, 55334418, 36144824, 0, 4604982, 2746453, 582024, 1339668, 767373, 0, 71616, 0]


len(nc17_domestic)

35


nc17_foreign = [17400000, 12775651, 16410548, 17266048, 6828348, 257833, 3664733, 43414417, 3367465, 
               60562448, 0, 261944, 0, 16410548, 1308406, 0, 2686353, 0, 797, 820812, 38894, 634741, 0,
               13000000, 45838620, 2887, 0, 60562448, 3000000, 45263, 574498, 1794447, 0, 950532, 0]
print(nc17_foreign) #showing the nc17_foreign list

[17400000, 12775651, 16410548, 17266048, 6828348, 257833, 3664733, 43414417, 3367465, 60562448, 0, 261944, 0, 16410548, 1308406, 0, 2686353, 0, 797, 820812, 38894, 634741, 0, 13000000, 45838620, 2887, 0, 60562448, 3000000, 45263, 574498, 1794447, 0, 950532, 0]


len(nc17_foreign)

35


nc17_worldwide = [37750754, 15307113, 20412841, 19465835, 16566240, 2315026, 3822241, 213120004, 4659110,
                 65167430, 1236844, 2661944, 205569, 20412841, 2094302, 3453416, 2783535, 103093, 
                 50283563, 3894240, 2038916, 690872, 9000000, 20412216, 101173038, 36147711	, 413802,
                 65167430, 5746453, 627287, 1914166, 2561820, 1008404, 1022148, 1470809]
print(nc17_worldwide) #showing the nc17_worldwide list

[37750754, 15307113, 20412841, 19465835, 16566240, 2315026, 3822241, 213120004, 4659110, 65167430, 1236844, 2661944, 205569, 20412841, 2094302, 3453416, 2783535, 103093, 50283563, 3894240, 2038916, 690872, 9000000, 20412216, 101173038, 36147711, 413802, 65167430, 5746453, 627287, 1914166, 2561820, 1008404, 1022148, 1470809]


len(nc17_worldwide)

35


nc17_runtime = [97, 130, 101, 180, 120, 84, 99, 89, 102, 158, 187, 85, 96, 101, 145, 155, 108, 94, 119,
               62, 96, 95, 109, 91, 112, 129, 92, 158, 134, 95, 84, 98, 80, 110, 82]
print(nc17_runtime) #showing the nc17_runtime list

[97, 130, 101, 180, 120, 84, 99, 89, 102, 158, 187, 85, 96, 101, 145, 155, 108, 94, 119, 62, 96, 95, 109, 91, 112, 129, 92, 158, 134, 95, 84, 98, 80, 110, 82]


len(nc17_runtime)

35


nc17_rating = [4.9, 7.1, 7.2, 7.7, 7.4, 5.5, 5.6, 5.9, 6.7, 7.5, 7.1, 7.4, 7.4, 7.2, 6.9, 6.7, 6.2, 6.4,
              7.2, 7.7, 7.0, 6.2, 6.1, 7.0, 7.8, 6.9, 6.0, 7.5, 7.7, 6.1, 5.1, 6.4, 5.5, 5.0, 7.1]
print(nc17_rating) #showing the nc17_rating list

[4.9, 7.1, 7.2, 7.7, 7.4, 5.5, 5.6, 5.9, 6.7, 7.5, 7.1, 7.4, 7.4, 7.2, 6.9, 6.7, 6.2, 6.4, 7.2, 7.7, 7.0, 6.2, 6.1, 7.0, 7.8, 6.9, 6.0, 7.5, 7.7, 6.1, 5.1, 6.4, 5.5, 5.0, 7.1]


len(nc17_rating)

35


nc17_genre = []
for i in range(35):nc17_genre.append('Drama')
print(nc17_genre) #showing the nc17_genre list

['Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama', 'Drama']


len(nc17_genre)

35


nc17_rated = []
for i in range(35):nc17_rated.append('NC-17')
print(nc17_rated) #showing the nc17_rated list

['NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17', 'NC-17']


len(nc17_rated)

35


nc17_budget_x = []
for i in nc17_budget:
    nc17_budget_x.append("${:,.0f}".format(i))
print(nc17_budget_x) #showing the nc17_budget_x list

['$45,000,000', '$15,000,000', '$6,500,000', '$4,074,940', '$1,000,000', '$1,000,000', '$3,565,572', '$12,000,000', '$10,000,000', '$15,000,000', '$19,000,000', '$350,000', '$1,000,000', '$6,500,000', '$4,700,000', '$904,765', '$3,000,000', '$700,000', '$34,000,000', '$230,000', '$1,000,000', '$3,200,000', '$1,000,000', '$1,500,000', '$6,500,000', '$1,250,000', '$12,000', '$15,000,000', '$2,200,000', '$1,300,000', '$15,000,000', '$6,400,000', '$50,000', '$3,259,572', '$612,072']


len(nc17_budget_x)

35


nc17_domestic_x = []
for i in nc17_domestic:
    nc17_domestic_x.append("${:,.0f}".format(i))
print(nc17_domestic_x) #showing the nc17_domestic_x list

['$20,350,754', '$2,531,462', '$4,002,293', '$2,199,787', '$9,737,892', '$2,057,193', '$157,508', '$169,705,587', '$1,291,645', '$4,604,982', '$0', '$2,400,000', '$0', '$4,002,293', '$785,896', '$0', '$97,182', '$0', '$50,282,766', '$3,073,428', '$2,000,022', '$56,131', '$0', '$7,412,216', '$55,334,418', '$36,144,824', '$0', '$4,604,982', '$2,746,453', '$582,024', '$1,339,668', '$767,373', '$0', '$71,616', '$0']


len(nc17_domestic_x)

35


nc17_foreign_x = []
for i in nc17_foreign:
    nc17_foreign_x.append("${:,.0f}".format(i))
print(nc17_foreign_x) #showing the nc17_foreign_x list

['$17,400,000', '$12,775,651', '$16,410,548', '$17,266,048', '$6,828,348', '$257,833', '$3,664,733', '$43,414,417', '$3,367,465', '$60,562,448', '$0', '$261,944', '$0', '$16,410,548', '$1,308,406', '$0', '$2,686,353', '$0', '$797', '$820,812', '$38,894', '$634,741', '$0', '$13,000,000', '$45,838,620', '$2,887', '$0', '$60,562,448', '$3,000,000', '$45,263', '$574,498', '$1,794,447', '$0', '$950,532', '$0']


len(nc17_foreign_x)

35


nc17_worldwide_x = []
for i in nc17_worldwide:
    nc17_worldwide_x.append("${:,.0f}".format(i))
print(nc17_worldwide_x) #showing the nc17_worldwide_x list

['$37,750,754', '$15,307,113', '$20,412,841', '$19,465,835', '$16,566,240', '$2,315,026', '$3,822,241', '$213,120,004', '$4,659,110', '$65,167,430', '$1,236,844', '$2,661,944', '$205,569', '$20,412,841', '$2,094,302', '$3,453,416', '$2,783,535', '$103,093', '$50,283,563', '$3,894,240', '$2,038,916', '$690,872', '$9,000,000', '$20,412,216', '$101,173,038', '$36,147,711', '$413,802', '$65,167,430', '$5,746,453', '$627,287', '$1,914,166', '$2,561,820', '$1,008,404', '$1,022,148', '$1,470,809']


len(nc17_worldwide_x)

35


nc17_profit = []
for x,y in enumerate(nc17_worldwide):
    nc17_profit.append(y-nc17_budget[x])
print(nc17_profit) #showing the nc17_profit list

[-7249246, 307113, 13912841, 15390895, 15566240, 1315026, 256669, 201120004, -5340890, 50167430, -17763156, 2311944, -794431, 13912841, -2605698, 2548651, -216465, -596907, 16283563, 3664240, 1038916, -2509128, 8000000, 18912216, 94673038, 34897711, 401802, 50167430, 3546453, -672713, -13085834, -3838180, 958404, -2237424, 858737]


len(nc17_profit)

35


nc17_profit_x = []
for i in nc17_profit:
    nc17_profit_x.append("${:,.0f}".format(i))
print(nc17_profit_x) #showing the nc17_profit_x list

['$-7,249,246', '$307,113', '$13,912,841', '$15,390,895', '$15,566,240', '$1,315,026', '$256,669', '$201,120,004', '$-5,340,890', '$50,167,430', '$-17,763,156', '$2,311,944', '$-794,431', '$13,912,841', '$-2,605,698', '$2,548,651', '$-216,465', '$-596,907', '$16,283,563', '$3,664,240', '$1,038,916', '$-2,509,128', '$8,000,000', '$18,912,216', '$94,673,038', '$34,897,711', '$401,802', '$50,167,430', '$3,546,453', '$-672,713', '$-13,085,834', '$-3,838,180', '$958,404', '$-2,237,424', '$858,737']


len(nc17_profit_x)

35


nc17_tickets = []
for i in nc17_worldwide:
    nc17_tickets.append(round(i/10))
print(nc17_tickets) #showing the nc17_tickets list

[3775075, 1530711, 2041284, 1946584, 1656624, 231503, 382224, 21312000, 465911, 6516743, 123684, 266194, 20557, 2041284, 209430, 345342, 278354, 10309, 5028356, 389424, 203892, 69087, 900000, 2041222, 10117304, 3614771, 41380, 6516743, 574645, 62729, 191417, 256182, 100840, 102215, 147081]


len(nc17_tickets)

35


nc17_tickets_x = []
for i in nc17_tickets:
    nc17_tickets_x.append("{:,.0f}".format(i))
print(nc17_tickets_x) #showing the nc17_tickets_x list

['3,775,075', '1,530,711', '2,041,284', '1,946,584', '1,656,624', '231,503', '382,224', '21,312,000', '465,911', '6,516,743', '123,684', '266,194', '20,557', '2,041,284', '209,430', '345,342', '278,354', '10,309', '5,028,356', '389,424', '203,892', '69,087', '900,000', '2,041,222', '10,117,304', '3,614,771', '41,380', '6,516,743', '574,645', '62,729', '191,417', '256,182', '100,840', '102,215', '147,081']


len(nc17_tickets_x)

35


nc17_dataframe =  pd.DataFrame({"Movie":nc17_name, "Release_Date":nc17_date, "Genre":nc17_genre,
                            "Rating":nc17_rated, 
                            "Production_Budget":nc17_budget, "Production_Budget_x":nc17_budget_x, 
                            "Domestic_Gross":nc17_domestic, "Domestic_Gross_x":nc17_domestic_x, 
                            "Foreign_Gross":nc17_foreign, "Foreign_Gross_x":nc17_foreign_x, 
                            "Worldwide_Gross":nc17_worldwide, "Worldwide_Gross_x":nc17_worldwide_x, 
                            "Profit":nc17_profit, "Profit_x":nc17_profit_x, "Tickets":nc17_tickets, 
                            "Tickets_x":nc17_tickets_x, "Runtime":nc17_runtime, "Averagerating":nc17_rating, 
                            "Company":nc17_company, "Star":nc17_star, "Director":nc17_director, "Writer":nc17_writer
                             })


nc17_dataframe.head()


Drama_DataFrame = Drama_DataFrame.append(nc17_dataframe, ignore_index=True)

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\1741375482.py:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  Drama_DataFrame = Drama_DataFrame.append(nc17_dataframe, ignore_index=True)


grouped2 = []
for i,x in enumerate(Drama_DataFrame.Rating):
    if Drama_DataFrame.Genre[i] == 'Drama':grouped2.append(Drama_DataFrame.Rating[i])
grouped2 = Counter(grouped2)
grouped2

Counter({'PG': 67, 'R': 77, 'PG-13': 76, 'Not Rated': 3, 'NC-17': 49, 'G': 34})


new = []
for i in  Drama_DataFrame.Worldwide_Gross:
    if isinstance(i, str):new.append(int(i.replace("$","").replace(",","")))
    else:new.append(i)
print(new) #showing the new list

[180047784, 142634358, 693698673, 449948323, 634454789, 54462971, 368567189, 137551594, 47818913, 84154026, 381398492, 371350619, 90552675, 74966854, 134612435, 213591522, 179748880, 108660270, 41642166, 26387039, 71004627, 203127894, 48478084, 570998101, 162498338, 169590606, 16340767, 31124367, 116809717, 50647416, 173567581, 96068724, 97143987, 85309093, 252276928, 61721826, 24687524, 63802928, 165552290, 160558438, 15826984, 197618160, 68984536, 16481405, 94050951, 15815509, 41059418, 213120004, 142033509, 96633833, 66540205, 29847480, 82917283, 6792768, 64282881, 77735925, 32398681, 31054727, 4065020, 38017873, 5046038, 304604712, 92678948, 208265198, 46604054, 22281732, 28270399, 3727746, 76086711, 14189810, 7680250, 7719630, 334522294, 38028230, 52545707, 56506120, 8217571, 7585011, 128955898, 20601987, 59168692, 11173718, 528731, 34044909, 331266710, 38358392, 33069303, 36262783, 11831131, 32909437, 19859167, 23477345, 35830713, 12034913, 42843521, 78356170, 62076141, 56178935, 70133905, 61603136, 31556959, 2179623, 36787044, 21817298, 81831866, 21971021, 77733867, 50827466, 31187727, 36964656, 10765283, 382946, 20412841, 16369708, 148806510, 41699612, 17499242, 18945682, 2821010, 6205034, 17536004, 4972016, 1027760, 1200000, 57273049, 679482, 40454520, 20433227, 38969037, 73975239, 23251930, 15298355, 35185884, 16610760, 16131551, 11295324, 10153415, 2088390, 7482387, 6328516, 21270290, 12231500, 14244931, 5552584, 16566240, 5438911, 1156309, 852399, 354836, 3728400, 62375, 2102779, 429448, 2769782, 9709597, 46918287, 542351353, 73986904, 305937718, 216601214, 38102988, 27118000, 534816, 37306334, 47494916, 19344615, 38741732, 114830111, 43545364, 18948425, 3438735, 137587063, 64605762, 33473297, 89137047, 8526288, 64667874, 106269971, 35656130, 3987768, 7025496, 152036382, 171120329, 13835130, 14859394, 134582776, 6101815, 63954968, 10769960, 32255440, 15164458, 127956187, 2819485, 43440294, 17815212, 157297525, 35856053, 119285432, 40716963, 14920781, 3281232, 14923752, 125052686, 549368315, 6668025, 199078, 64892670, 4786789, 8443124, 2044892, 2400000, 1705908, 80008942, 48000000, 17356268, 1008404, 277845, 1614784, 20412216, 20350754, 98410061, 496059, 15121165, 1022148, 67091915, 20412841, 19465835, 195494, 2411143, 1025228, 18587135, 8721243, 40300, 10015449, 80693537, 54766923, 77211836, 34718173, 1951683, 636796, 2447576, 9171289, 3256082, 13000000, 11000000, 438656843, 66947950, 27469621, 37799643, 325500000, 246100000, 3750000, 69131860, 4517000, 143985708, 10015449, 17657973, 80491516, 311281000, 286214195, 90482317, 986214868, 268000000, 72071636, 108998, 47707417, 30194409, 65500000, 7600377, 12000000, 592861, 37750754, 15307113, 20412841, 19465835, 16566240, 2315026, 3822241, 213120004, 4659110, 65167430, 1236844, 2661944, 205569, 20412841, 2094302, 3453416, 2783535, 103093, 50283563, 3894240, 2038916, 690872, 9000000, 20412216, 101173038, 36147711, 413802, 65167430, 5746453, 627287, 1914166, 2561820, 1008404, 1022148, 1470809]


len(new)

306


Drama_DataFrame.Worldwide_Gross = new


new1 = []
for i in  Drama_DataFrame.Worldwide_Gross_x:
    if isinstance(i, int):new1.append('${:,.0f}'.format(i))
    else:new1.append(i)
print(new1) #showing the new1 list

['$180,047,784', '$142,634,358', '$693,698,673', '$449,948,323', '$634,454,789', '$54,462,971', '$368,567,189', '$137,551,594', '$47,818,913', '$84,154,026', '$381,398,492', '$371,350,619', '$90,552,675', '$74,966,854', '$134,612,435', '$213,591,522', '$179,748,880', '$108,660,270', '$41,642,166', '$26,387,039', '$71,004,627', '$203,127,894', '$48,478,084', '$570,998,101', '$162,498,338', '$169,590,606', '$16,340,767', '$31,124,367', '$116,809,717', '$50,647,416', '$173,567,581', '$96,068,724', '$97,143,987', '$85,309,093', '$252,276,928', '$61,721,826', '$24,687,524', '$63,802,928', '$165,552,290', '$160,558,438', '$15,826,984', '$197,618,160', '$68,984,536', '$16,481,405', '$94,050,951', '$15,815,509', '$41,059,418', '$213,120,004', '$142,033,509', '$96,633,833', '$66,540,205', '$29,847,480', '$82,917,283', '$6,792,768', '$64,282,881', '$77,735,925', '$32,398,681', '$31,054,727', '$4,065,020', '$38,017,873', '$5,046,038', '$304,604,712', '$92,678,948', '$208,265,198', '$46,604,054', '$22,281,732', '$28,270,399', '$3,727,746', '$76,086,711', '$14,189,810', '$7,680,250', '$7,719,630', '$334,522,294', '$38,028,230', '$52,545,707', '$56,506,120', '$8,217,571', '$7,585,011', '$128,955,898', '$20,601,987', '$59,168,692', '$11,173,718', '$528,731', '$34,044,909', '$331,266,710', '$38,358,392', '$33,069,303', '$36,262,783', '$11,831,131', '$32,909,437', '$19,859,167', '$23,477,345', '$35,830,713', '$12,034,913', '$42,843,521', '$78,356,170', '$62,076,141', '$56,178,935', '$70,133,905', '$61,603,136', '$31,556,959', '$2,179,623', '$36,787,044', '$21,817,298', '$81,831,866', '$21,971,021', '$77,733,867', '$50,827,466', '$31,187,727', '$36,964,656', '$10,765,283', '$382,946', '$20,412,841', '$16,369,708', '$148,806,510', '$41,699,612', '$17,499,242', '$18,945,682', '$2,821,010', '$6,205,034', '$17,536,004', '$4,972,016', '$1,027,760', '$1,200,000', '$57,273,049', '$679,482', '$40,454,520', '$20,433,227', '$38,969,037', '$73,975,239', '$23,251,930', '$15,298,355', '$35,185,884', '$16,610,760', '$16,131,551', '$11,295,324', '$10,153,415', '$2,088,390', '$7,482,387', '$6,328,516', '$21,270,290', '$12,231,500', '$14,244,931', '$5,552,584', '$16,566,240', '$5,438,911', '$1,156,309', '$852,399', '$354,836', '$3,728,400', '$62,375', '$2,102,779', '$429,448', '$2,769,782', '$9,709,597', '$46,918,287', '$542,351,353', '$73,986,904', '$305,937,718', '$216,601,214', '$38,102,988', '$27,118,000', '$534,816', '$37,306,334', '$47,494,916', '$19,344,615', '$38,741,732', '$114,830,111', '$43,545,364', '$18,948,425', '$3,438,735', '$137,587,063', '$64,605,762', '$33,473,297', '$89,137,047', '$8,526,288', '$64,667,874', '$106,269,971', '$35,656,130', '$3,987,768', '$7,025,496', '$152,036,382', '$171,120,329', '$13,835,130', '$14,859,394', '$134,582,776', '$6,101,815', '$63,954,968', '$10,769,960', '$32,255,440', '$15,164,458', '$127,956,187', '$2,819,485', '$43,440,294', '$17,815,212', '$157,297,525', '$35,856,053', '$119,285,432', '$40,716,963', '$14,920,781', '$3,281,232', '$14,923,752', '$125,052,686', '$549,368,315', '$6,668,025', '$199,078', '$64,892,670', '$4,786,789', '$8,443,124', '$2,044,892', '$2,400,000', '$1,705,908', '$80,008,942', '$48,000,000', '$17,356,268', '$1,008,404', '$277,845', '$1,614,784', '$20,412,216', '$20,350,754', '$98,410,061', '$496,059', '$15,121,165', '$1,022,148', '$67,091,915', '$20,412,841', '$19,465,835', '$195,494', '$2,411,143', '$1,025,228', '$18,587,135', '$8,721,243', '$40,300', '$10,015,449', '$80,693,537', '$54,766,923', '$77,211,836', '$34,718,173', '$1,951,683', '$636,796', '$2,447,576', '$9,171,289', '$3,256,082', '$13,000,000', '$11,000,000', '$438,656,843', '$66,947,950', '$27,469,621', '$37,799,643', '$325,500,000', '$246,100,000', '$3,750,000', '$69,131,860', '$4,517,000', '$143,985,708', '$10,015,449', '$17,657,973', '$80,491,516', '$311,281,000', '$286,214,195', '$90,482,317', '$986,214,868', '$268,000,000', '$72,071,636', '$108,998', '$47,707,417', '$30,194,409', '$65,500,000', '$7,600,377', '$12,000,000', '$592,861', '$37,750,754', '$15,307,113', '$20,412,841', '$19,465,835', '$16,566,240', '$2,315,026', '$3,822,241', '$213,120,004', '$4,659,110', '$65,167,430', '$1,236,844', '$2,661,944', '$205,569', '$20,412,841', '$2,094,302', '$3,453,416', '$2,783,535', '$103,093', '$50,283,563', '$3,894,240', '$2,038,916', '$690,872', '$9,000,000', '$20,412,216', '$101,173,038', '$36,147,711', '$413,802', '$65,167,430', '$5,746,453', '$627,287', '$1,914,166', '$2,561,820', '$1,008,404', '$1,022,148', '$1,470,809']


len(new1)

306


Drama_DataFrame.Worldwide_Gross_x = new1


pd.set_option('display.max_columns', None)#showing all the columns
Drama_DataFrame


from itables import init_notebook_mode
init_notebook_mode(all_interactive=True)


Drama_DataFrame


r_index = []
for i,x in enumerate(Drama_DataFrame.Rating):
    if x == 'R':r_index.append(i)
print(r_index) #showing the r_index list

[1, 3, 5, 6, 9, 10, 11, 13, 14, 23, 29, 36, 39, 53, 55, 56, 57, 58, 59, 64, 66, 67, 71, 76, 77, 81, 82, 84, 85, 87, 88, 90, 92, 93, 94, 97, 98, 101, 103, 106, 110, 111, 116, 118, 120, 121, 124, 125, 126, 127, 128, 130, 133, 134, 135, 136, 137, 139, 140, 142, 144, 145, 146, 147, 150, 152, 153, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244]


len(r_index)

77


r_profit = []
for i in r_index:
        r_profit.append(Drama_DataFrame.Profit[i])
print(r_profit) #showing the r_profit list

[-7365642.0, 349948323.0, -13537029.0, 307567189.0, 24154026.0, 326398492.0, 316350619.0, 19966854.0, 82112435.0, 530998101.0, 13147416.0, -10312476.0, 129558438.0, -18207232.0, 54735925.0, 9898681.0, 8554727.0, -17934980.0, 17017873.0, 26604054.0, 8270399.0, -16272254.0, -10280370.0, -7782429.0, -8414989.0, -3826282.0, -14471269.0, 318266710.0, 25358392.0, 23262783.0, -1168869.0, 7859167.0, 23830713.0, 34913.0, 31043521.0, 45178935.0, 60133905.0, -7820377.0, 12417298.0, 69233867.0, 3765283.0, -6617054.0, 12499242.0, -2178990.0, 12636004.0, 222016.0, 53273049.0, -3320518.0, 36954520.0, 17033227.0, 35669037.0, 20251930.0, 14610760.0, 14131551.0, 9295324.0, 8153415.0, 88390.0, 4328516.0, 19282640.0, 12744931.0, 15566240.0, 4438911.0, 156309.0, -147601.0, -187625.0, 294448.0, 2669782.0, 48766923.0, 68711836.0, 14718173.0, 1851683.0, -25363204.0, -4052424.0, -12828711.0, 556082.0, 1500000.0, 2000000.0]


len(r_profit)

77


r_cost = []
for i in r_index:
        r_cost.append(Drama_DataFrame.Production_Budget_x[i])
print(r_cost) #showing the r_cost list

['$150,000,000', '$100,000,000', '$68,000,000', '$61,000,000', '$60,000,000', '$55,000,000', '$55,000,000', '$55,000,000', '$52,500,000', '$40,000,000', '$37,500,000', '$35,000,000', '$31,000,000', '$25,000,000', '$23,000,000', '$22,500,000', '$22,500,000', '$22,000,000', '$21,000,000', '$20,000,000', '$20,000,000', '$20,000,000', '$18,000,000', '$16,000,000', '$16,000,000', '$15,000,000', '$15,000,000', '$13,000,000', '$13,000,000', '$13,000,000', '$13,000,000', '$12,000,000', '$12,000,000', '$12,000,000', '$11,800,000', '$11,000,000', '$10,000,000', '$10,000,000', '$9,400,000', '$8,500,000', '$7,000,000', '$7,000,000', '$5,000,000', '$5,000,000', '$4,900,000', '$4,750,000', '$4,000,000', '$4,000,000', '$3,500,000', '$3,400,000', '$3,300,000', '$3,000,000', '$2,000,000', '$2,000,000', '$2,000,000', '$2,000,000', '$2,000,000', '$2,000,000', '$1,987,650', '$1,500,000', '$1,000,000', '$1,000,000', '$1,000,000', '$1,000,000', '$250,000', '$135,000', '$100,000', '$6,000,000', '$8,500,000', '$20,000,000', '$100,000', '$26,000,000', '$6,500,000', '$22,000,000', '$2,700,000', '$11,500,000', '$9,000,000']


len(r_cost)

77


r_name = []
for i in r_index:
        r_name.append(Drama_DataFrame.Movie[i])
print(r_name) #showing the r_name list

['The Wolfman', 'Django Unchained', 'Downsizing', 'Gone Girl', 'Priest', 'Fifty Shades Darker', 'Fifty Shades Freed', 'Crimson Peak', 'Zero Dark Thirty', 'Fifty Shades of Grey', 'The Master', 'Biutiful', 'Flight', 'Tulip Fever', 'The Ides of March', 'Nocturnal Animals', 'The Water Diviner', 'Stone', 'For Colored Girls', 'The Debt', 'Let Me In', 'By the Sea', 'Miss Sloane', 'The Homesman', 'The Immigrant', 'Never Let Me Go', 'The Reluctant Fundamentalist', 'Black Swan', 'Ex Machina', 'Room', 'Chloe', 'If Beale Street Could Talk', 'Arbitrage', 'Stoker', 'Carol', 'Quartet', 'Hereditary', 'Coriolanus', 'Melancholia', 'Manchester by the Sea', 'We Need to Talk About Kevin', 'Hesher', 'Addicted', 'Everything Must Go', 'Mommy', 'Take Shelter', 'Boyhood', 'Stake Land', 'The Witch', 'Margin Call', 'Whiplash', 'Before Midnight', 'Silent House', "Winter's Bone", 'The Florida Project', 'We Are Your Friends', 'Locke', 'Knock Knock', 'Buried', 'Unsane', 'Blue Valentine', 'Martha Marcy May Marlene', 'Palo Alto', 'I Origins', 'The Canyons', 'Sound of My Voice', 'A Ghost Story', 'Ordinary People', 'Fame', 'Endless Love', 'Ghost Story', 'One from the Heart', 'The Hand', 'Pennies from Heaven', 'Zoot Suit', 'Rich and Famous', 'Raggedy Man']


len(r_name)

77


r_return_on_investment = []
for i in r_index:
        r_return_on_investment.append(Drama_DataFrame.Profit_x[i])
print(r_return_on_investment) #showing the r_return_on_investment list

['$-7,365,642', '$349,948,323', '$-13,537,029', '$307,567,189', '$24,154,026', '$326,398,492', '$316,350,619', '$19,966,854', '$82,112,435', '$530,998,101', '$13,147,416', '$-10,312,476', '$129,558,438', '$-18,207,232', '$54,735,925', '$9,898,681', '$8,554,727', '$-17,934,980', '$17,017,873', '$26,604,054', '$8,270,399', '$-16,272,254', '$-10,280,370', '$-7,782,429', '$-8,414,989', '$-3,826,282', '$-14,471,269', '$318,266,710', '$25,358,392', '$23,262,783', '$-1,168,869', '$7,859,167', '$23,830,713', '$34,913', '$31,043,521', '$45,178,935', '$60,133,905', '$-7,820,377', '$12,417,298', '$69,233,867', '$3,765,283', '$-6,617,054', '$12,499,242', '$-2,178,990', '$12,636,004', '$222,016', '$53,273,049', '$-3,320,518', '$36,954,520', '$17,033,227', '$35,669,037', '$20,251,930', '$14,610,760', '$14,131,551', '$9,295,324', '$8,153,415', '$88,390', '$4,328,516', '$19,282,640', '$12,744,931', '$15,566,240', '$4,438,911', '$156,309', '$-147,601', '$-187,625', '$294,448', '$2,669,782', '$48,766,923', '$68,711,836', '$14,718,173', '$1,851,683', '$-25,363,204', '$-4,052,424', '$-12,828,711', '$556,082', '$1,500,000', '$2,000,000']


len(r_return_on_investment)

77


r_rating = []
for i in r_index:
        r_rating.append(Drama_DataFrame.Averagerating[i])
print(r_rating) #showing the r_rating list

[5.8, 8.4, 5.7, 8.1, 5.7, 4.6, 4.5, 6.5, 7.4, 4.1, 7.1, 7.5, 7.3, 6.2, 7.1, 7.5, 7.1, 5.6, 6.1, 6.9, 7.1, 5.3, 7.5, 6.6, 6.6, 7.1, 6.9, 8.0, 7.7, 8.2, 6.9, 7.2, 6.6, 6.8, 7.2, 6.8, 7.3, 8.7, 7.2, 7.8, 7.5, 7.0, 5.2, 6.4, 8.1, 7.4, 7.9, 6.5, 6.8, 7.1, 8.5, 7.9, 5.3, 7.2, 7.6, 6.2, 7.1, 4.9, 7.0, 6.4, 7.4, 6.9, 6.2, 7.4, 3.8, 6.6, 6.8, 7.7, 6.6, 4.9, 6.3, 6.5, 5.5, 6.5, 6.8, 5.9, 6.8]


len(r_rating)

77


r_percent_profit = []
for i in r_index:
    i = (Drama_DataFrame.Profit[i] / Drama_DataFrame.Production_Budget[i])*100
    r_percent_profit.append(int(round(i,0)))
print(r_percent_profit) #showing the r_percent_profit list

[-5, 350, -20, 504, 40, 593, 575, 36, 156, 1327, 35, -29, 418, -73, 238, 44, 38, -82, 81, 133, 41, -81, -57, -49, -53, -26, -96, 2448, 195, 179, -9, 65, 199, 0, 263, 411, 601, -78, 132, 815, 54, -95, 250, -44, 258, 5, 1332, -83, 1056, 501, 1081, 675, 731, 707, 465, 408, 4, 216, 970, 850, 1557, 444, 16, -15, -75, 218, 2670, 813, 808, 74, 1852, -98, -62, -58, 21, 13, 22]


len(r_percent_profit)

77


r_roi_percent = []
for i in r_percent_profit:
    r_roi_percent.append("{:}%".format(i))
print(r_roi_percent) #showing the r_roi_percent list

['-5%', '350%', '-20%', '504%', '40%', '593%', '575%', '36%', '156%', '1327%', '35%', '-29%', '418%', '-73%', '238%', '44%', '38%', '-82%', '81%', '133%', '41%', '-81%', '-57%', '-49%', '-53%', '-26%', '-96%', '2448%', '195%', '179%', '-9%', '65%', '199%', '0%', '263%', '411%', '601%', '-78%', '132%', '815%', '54%', '-95%', '250%', '-44%', '258%', '5%', '1332%', '-83%', '1056%', '501%', '1081%', '675%', '731%', '707%', '465%', '408%', '4%', '216%', '970%', '850%', '1557%', '444%', '16%', '-15%', '-75%', '218%', '2670%', '813%', '808%', '74%', '1852%', '-98%', '-62%', '-58%', '21%', '13%', '22%']


len(r_roi_percent)

77


r_stars = []
for i in r_rating:
    r_stars.append('*'*int(i))
print(r_stars) #showing the r_stars list

['*****', '********', '*****', '********', '*****', '****', '****', '******', '*******', '****', '*******', '*******', '*******', '******', '*******', '*******', '*******', '*****', '******', '******', '*******', '*****', '*******', '******', '******', '*******', '******', '********', '*******', '********', '******', '*******', '******', '******', '*******', '******', '*******', '********', '*******', '*******', '*******', '*******', '*****', '******', '********', '*******', '*******', '******', '******', '*******', '********', '*******', '*****', '*******', '*******', '******', '*******', '****', '*******', '******', '*******', '******', '******', '*******', '***', '******', '******', '*******', '******', '****', '******', '******', '*****', '******', '******', '*****', '******']


len(r_stars)

77


system_rating_r = pd.DataFrame({"Name of Movie":r_name, "Cost":r_cost, 
                                "Return On Investment":r_return_on_investment, 
                                "ROI Percentage":r_roi_percent,"Ratings":r_stars})


system_rating_r


neg_values = []
for i,x in enumerate(r_percent_profit): 
    if x <= 0: neg_values.append(i)
print(neg_values) #showing the neg_values list

[0, 2, 11, 13, 17, 21, 22, 23, 24, 25, 26, 30, 33, 37, 41, 43, 47, 63, 64, 71, 72, 73]


len(neg_values)

22


system_rating_r = system_rating_r.drop(labels=neg_values, axis=0)
system_rating_r = system_rating_r.reset_index(drop=True)


system_rating_r


system_rating_r1=system_rating_r[:19]
system_rating_r1


system_rating_r2=system_rating_r[19:37]
system_rating_r2


system_rating_r3=system_rating_r[37:]
system_rating_r3


r_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_r['Cost']]) / len(system_rating_r['Cost'])


r_avg_value

16455866.363636363


r_cost_index = [int(i.replace('$', '').replace(',', ''))for i in system_rating_r['Cost']]
#above ayg
r_below_avg1 = []
for i,x in enumerate(r_cost_index):
    if x <= 16455866:r_below_avg1.append(i)
    
r_below_avg2 = []
for i,x in enumerate(r_cost_index):
    if x >= 16455866:r_below_avg2.append(i)


print(r_below_avg1)

[16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 51, 52, 53, 54]


print(r_below_avg2)

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 50]


r_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_r['Return On Investment']]) / len(system_rating_r['Cost'])


r_avg_value

59600710.27272727


r_roi_index = [int(i.replace('$', '').replace(',', ''))for i in system_rating_r['Return On Investment']]
#below ayg
r_below_avg3 = []
for i,x in enumerate(r_roi_index):
    if x <= 59600710:r_below_avg3.append(i)
    
r_below_avg4 = []
for i,x in enumerate(r_roi_index):
    if x >= 59600710:r_below_avg4.append(i)


print(r_below_avg3)

[2, 5, 8, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 24, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 50, 51, 52, 53, 54]


print(r_below_avg4)

[0, 1, 3, 4, 6, 7, 9, 16, 23, 25, 49]


r_avg_value = sum([int(i.replace('%', ''))
                 for i in system_rating_r['ROI Percentage']]) / len(system_rating_r['Cost'])


r_avg_value

508.8727272727273


roi_percent_index_r = [int(i.replace('%', ''))for i in system_rating_r['ROI Percentage']]
#above ayg
r_above_avg = []
for i,x in enumerate(roi_percent_index_r):
    if x >= 508:r_above_avg.append(i)


r_above_avg

[3, 4, 7, 16, 23, 25, 30, 31, 33, 34, 35, 36, 41, 42, 43, 47, 48, 49, 51]


def Ratings1(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(19):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight2(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(19):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#ff5500;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
    return df 


def highlight_cells3(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in r_below_avg1[:3]:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells4(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in r_below_avg2[:-1]:
        df.iloc[i,1] = 'background-color:#ff5500;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells5(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in r_below_avg3[:11]:
        df.iloc[i,2] = 'background-color:#ff5500;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells6(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in r_below_avg4[:8]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells7(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in r_above_avg[:4]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 

def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_r1=system_rating_r1.style.apply(Ratings_highlight2, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #ff5500')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#ff5500")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#ff5500')]}#index
                         ])\
            .apply(Ratings1, axis=None)\
            .apply(highlight_cells3, axis=None)\
            .apply(highlight_cells4, axis=None)\
            .apply(highlight_cells5, axis=None)\
            .apply(highlight_cells6, axis=None)\
            .apply(highlight_cells7, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


def Ratings8(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):#range(19,37):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight9(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#ff5500;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
    return df 

def highlight_cells10(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):#below_avg1[3:21]
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 


def highlight_cells11(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):#below_avg3[11:27]:
        df.iloc[i,2] = 'background-color:#ff5500;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells12(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [4, 6]:#below_avg3[11:27]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 


def highlight_cells13(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [4, 6,  11, 12, 14, 15, 16, 17]:#above_avg[4:12]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 

def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 

system_rating_r2 = system_rating_r2.style.apply(Ratings_highlight9, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #ff5500')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#ff5500")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#ff5500')]}#index
                         ])\
            .apply(Ratings8, axis=None)\
            .apply(highlight_cells10, axis=None)\
            .apply(highlight_cells11, axis=None)\
            .apply(highlight_cells12, axis=None)\
            .apply(highlight_cells13, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 2')
            #.apply(borders, axis=None)
            #display_html(df1_style._repr_html_() + df2_style._repr_html_(), raw=True)


def Ratings14(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight15(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#ff5500;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
    return df 

def highlight_cells16(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells17(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[13,1] = 'background-color:#ff5500;color:white;border-bottom: 2px solid black'
    return df 


def highlight_cells18(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(18):
        df.iloc[i,2] = 'background-color:#ff5500;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells19(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[12,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 


def highlight_cells20(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [4, 5, 6, 10, 11, 12, 14]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 

def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 

system_rating_r3 = system_rating_r3.style.apply(Ratings_highlight15, axis=None)\
            .apply(Ratings14, axis=None)\
            .apply(highlight_cells16, axis=None)\
            .apply(highlight_cells17, axis=None)\
            .apply(highlight_cells18, axis=None)\
            .apply(highlight_cells19, axis=None)\
            .apply(highlight_cells20, axis=None)\
            .set_table_attributes("style='display:inline'")\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #ff5500')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#ff5500")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#ff5500')]}#index
                              ])\
            .set_properties(**{'text-align': 'center'})
                         
            #.set_caption('Caption table 3')
            #.apply(borders, axis=None)


dfi.export(system_rating_r1, 'system_rating_r1.png')


dfi.export(system_rating_r2, 'system_rating_r2.png')


dfi.export(system_rating_r3, 'system_rating_r3.png')


def display_side_by_side(*args):
    html_str = "<center><font size=6 style='color:#ff5500'>The Return On Investement on R-rated Movies.</font></center> <br>  " 
 
    for df in args:
        html_str += df.to_html()
    display_html(
        html_str.replace('table','table style="display:inline"'), 
        raw=True
    )


g_index = []
for i,x in enumerate(Drama_DataFrame.Rating):
    if x == 'G':g_index.append(i)
print(g_index) #showing the g_index list

[227, 228, 229, 230, 231, 232, 233, 234, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270]


len(g_index)

34


g_cost = []
for i in g_index:
        g_cost.append(Drama_DataFrame.Production_Budget_x[i])
print(g_cost) #showing the g_index list

['$35,446,775', '$700,000', '$8,600,000', '$7,000,000', '$18,000,000', '$4,400,000', '$17,000,000', '$22,000,000', '$20,000,000', '$23,000,000', '$15,000,000', '$2,700,000', '$70,000,000', '$30,000,000', '$2,500,000', '$90,000,000', '$666,000', '$85,000,000', '$17,000,000', '$10,000,000', '$22,000,000', '$18,000,000', '$8,200,000', '$60,000,000', '$45,000,000', '$858,000', '$17,000,000', '$300,000', '$10,000,000', '$6,400,000', '$13,000,000', '$1,750,000', '$1,700,000', '$3,000,000']


len(g_cost)

34


g_name = []
for i in g_index:
        g_name.append(Drama_DataFrame.Movie[i])
print(g_name) #showing the g_name list

['La traviata', 'A Sunday in the Country', 'Little Dorrit', 'Prancer', 'The Secret Garden', 'Through the Olive Trees', 'A Little Princess', 'The Rookie', 'Beauty and the Beast 1991', 'The Little Rascals', 'Ramona and Beezus', 'The Black Stallion', 'The Hunchback of Notre Drame', 'Babe', 'Pollyanna', 'Babe: Pig in the City', 'Lassie Come Home', "Charlotte's Web", 'A Little Princess', 'Kit Kittredge: An American Girl', 'The Rookie', 'The Secret Garden', 'The Sound of Music', 'The Tale of Despereaux', 'The Lion King 1994', 'Bambi 1942', 'My Fair Lady 1964', 'Before the Wrath', "Hachiko: A Dog's Story", 'Giant', 'The Ten Commandments 1966', 'The Quiet Man', 'Three Cions in the Fountain', 'Miracle of Marcelino']


len(g_name)

34


g_return_on_investment = []
for i in g_index:
        g_return_on_investment.append(Drama_DataFrame.Profit_x[i])
print(g_return_on_investment) #showing the g_return_on_investment list

['$-35,251,281', '$1,711,143', '$-7,574,772', '$11,587,135', '$-9,278,757', '$-4,359,700', '$-6,984,551', '$58,693,537', '$418,656,843', '$43,947,950', '$12,469,621', '$35,099,643', '$255,500,000', '$216,100,000', '$1,250,000', '$-20,868,140', '$3,851,000', '$58,985,708', '$-6,984,551', '$7,657,973', '$58,491,516', '$293,281,000', '$278,014,195', '$30,482,317', '$941,214,868', '$267,142,000', '$55,071,636', '$-191,002', '$37,707,417', '$23,794,409', '$52,500,000', '$5,850,377', '$10,300,000', '$-2,407,139']


len(g_return_on_investment)

34


g_rating = []
for i in g_index:
        g_rating.append(Drama_DataFrame.Averagerating[i])
print(g_rating) #showing the g_rating list

[7.2, 7.6, 7.3, 6.4, 7.3, 7.8, 7.7, 6.9, 8.0, 6.3, 6.5, 7.4, 7.0, 9.6, 9.0, 5.8, 7.1, 6.3, 7.6, 6.5, 6.9, 7.3, 8.1, 6.1, 8.5, 7.3, 7.8, 6.6, 8.1, 7.6, 7.9, 7.7, 6.3, 7.1]


len(g_rating)

34


g_percent_profit = []
for i in g_index:
    i = (Drama_DataFrame.Profit[i] / Drama_DataFrame.Production_Budget[i])*100
    g_percent_profit.append(int(round(i,0)))
print(g_percent_profit) #showing the g_percent_profit list

[-99, 244, -88, 166, -52, -99, -41, 267, 2093, 191, 83, 1300, 365, 720, 50, -23, 578, 69, -41, 77, 266, 1629, 3390, 51, 2092, 31135, 324, -64, 377, 372, 404, 334, 606, -80]


len(g_percent_profit)

34


g_roi_percent = []
for i in g_percent_profit:
    g_roi_percent.append("{:}%".format(i))
print(g_roi_percent) #showing the g_roi_percent list

['-99%', '244%', '-88%', '166%', '-52%', '-99%', '-41%', '267%', '2093%', '191%', '83%', '1300%', '365%', '720%', '50%', '-23%', '578%', '69%', '-41%', '77%', '266%', '1629%', '3390%', '51%', '2092%', '31135%', '324%', '-64%', '377%', '372%', '404%', '334%', '606%', '-80%']


len(g_roi_percent)

34


g_stars = []
for i in g_rating:
    g_stars.append('*'*int(i))
print(g_stars) #showing the g_stars list

['*******', '*******', '*******', '******', '*******', '*******', '*******', '******', '********', '******', '******', '*******', '*******', '*********', '*********', '*****', '*******', '******', '*******', '******', '******', '*******', '********', '******', '********', '*******', '*******', '******', '********', '*******', '*******', '*******', '******', '*******']


len(g_stars)

34


system_rating_g = pd.DataFrame({"Name of Movie":g_name, "Cost":g_cost, 
                                "Return On Investment":g_return_on_investment, 
                                "ROI Percentage":g_roi_percent,"Ratings":g_stars})


system_rating_g


neg_values = []
for i,x in enumerate(g_percent_profit): 
    if x <= 0: neg_values.append(i)
print(neg_values) #showing the neg_values list

[0, 2, 4, 5, 6, 15, 18, 27, 33]


len(neg_values)

9


system_rating_g = system_rating_g.drop(labels=neg_values, axis=0)
system_rating_g = system_rating_g.reset_index(drop=True)


system_rating_g


system_rating_g1=system_rating_g[:12]
system_rating_g1


system_rating_g2=system_rating_g[12:]
system_rating_g2


g_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_g['Cost']]) / len(system_rating_g['Cost'])


g_avg_value

19698960.0


g_cost_index = [int(i.replace('$', '').replace(',', ''))for i in system_rating_g['Cost']]
#below ayg
g_below_avg5 = []
for i,x in enumerate(g_cost_index):
    if x <= 19698960:g_below_avg5.append(i)
    
g_below_avg6 = []
for i,x in enumerate(g_cost_index):
    if x >= 19698960:g_below_avg6.append(i)


print(g_below_avg5)

[0, 1, 5, 6, 9, 10, 12, 14, 15, 18, 19, 20, 21, 22, 23, 24]


print(g_below_avg6)

[2, 3, 4, 7, 8, 11, 13, 16, 17]


g_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_g['Return On Investment']]) / len(system_rating_g['Cost'])


g_avg_value

127174411.52


g_roi_index = [int(i.replace('$', '').replace(',', ''))for i in system_rating_g['Return On Investment']]
#below ayg
g_below_avg7 = []
for i,x in enumerate(g_roi_index):
    if x <= 127174411:g_below_avg7.append(i)
    
g_below_avg8 = []
for i,x in enumerate(g_roi_index):
    if x >= 127174411:g_below_avg8.append(i)


print(g_below_avg7)

[0, 1, 2, 4, 5, 6, 9, 10, 11, 12, 13, 16, 19, 20, 21, 22, 23, 24]


print(g_below_avg8)

[3, 7, 8, 14, 15, 17, 18]


g_avg_value = sum([int(i.replace('%', ''))
                 for i in system_rating_g['ROI Percentage']]) / len(system_rating_g['Cost'])


g_avg_value

1887.32


roi_percent_index_g = [int(i.replace('%', ''))for i in system_rating_g['ROI Percentage']]
#below ayg
g_above_avg = []
for i,x in enumerate(roi_percent_index_g):
    if x >= 1887:g_above_avg.append(i)


g_above_avg

[3, 15, 17, 18]


def Ratings21(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(12):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight22(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(12):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:red;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
        df.iloc[i,1] = 'font-size:4pt'
    return df 


def highlight_cells23(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in g_below_avg5[:6]:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom:2px solid black'
    return df 

def highlight_cells24(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in g_below_avg6[:6]:
        df.iloc[i,1] = 'background-color:red;color:white;border-bottom:2px solid black'
    return df 

def highlight_cells25(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in g_below_avg7[:9]:
        df.iloc[i,2] = 'background-color:red;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells26(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in g_below_avg8[:3]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells27(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[3,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 


def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_g1=system_rating_g1.style.apply(Ratings_highlight22, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid red')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","red")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','red')]}#index
                         ])\
            .apply(Ratings21, axis=None)\
            .apply(highlight_cells23, axis=None)\
            .apply(highlight_cells24, axis=None)\
            .apply(highlight_cells25, axis=None)\
            .apply(highlight_cells26, axis=None)\
            .apply(highlight_cells27, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


def Ratings28(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(13):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight29(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(13):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:red;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
        df.iloc[i,1] = 'font-size:4pt'
    return df 


def highlight_cells30(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 2, 3, 6, 7, 8, 9, 10, 11, 12]:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom:2px solid black'
    return df 

def highlight_cells31(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [1,4,5]:
        df.iloc[i,1] = 'background-color:red;color:white;border-bottom:2px solid black'
    return df 

def highlight_cells32(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 1, 4, 7, 8, 9, 10, 11, 12]:
        df.iloc[i,2] = 'background-color:red;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells33(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [2, 3, 5, 6]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells34(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [3, 5, 6]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 


def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_g2=system_rating_g2.style.apply(Ratings_highlight29, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid red')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","red")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','red')]}#index
                         ])\
            .apply(Ratings28, axis=None)\
            .apply(highlight_cells30, axis=None)\
            .apply(highlight_cells31, axis=None)\
            .apply(highlight_cells32, axis=None)\
            .apply(highlight_cells33, axis=None)\
            .apply(highlight_cells34, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


dfi.export(system_rating_g1, 'system_rating_g1.png')


dfi.export(system_rating_g2, 'system_rating_g2.png')


def display_side_by_side2(*args):
    html_str = "<center><font size=6 style='color:red'>The Return On Investement on G-rated Movies.</font></center> <br>  " 
 
    for df in args:
        html_str += df.to_html()
    display_html(
        html_str.replace('table','table style="display:inline"'), 
        raw=True
    )


pg_index = []
for i,x in enumerate(Drama_DataFrame.Rating):
    if x == 'PG':pg_index.append(i)
print(pg_index) #showing the pg_index list

[0, 31, 40, 61, 62, 129, 141, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213]


len(pg_index)

67


pg_cost = []
for i in pg_index:
        pg_cost.append(Drama_DataFrame.Production_Budget_x[i])
print(pg_cost) #showing the pg_index list

['$180,000,000', '$37,000,000', '$31,000,000', '$20,000,000', '$20,000,000', '$3,000,000', '$1,700,000', '$5,100,000', '$10,000,000', '$95,000,000', '$3,000,000', '$20,000,000', '$40,000,000', '$5,000,000', '$422,000', '$5,100,000', '$72,000,000', '$11,800,000', '$15,000,000', '$32,000,000', '$40,000,000', '$65,000,000', '$8,000,000', '$9,000,000', '$17,000,000', '$30,000,000', '$500,000', '$20,000,000', '$11,000,000', '$2,000,000', '$23,000,000', '$45,000,000', '$15,000,000', '$10,000,000', '$32,000,000', '$90,000,000', '$10,000,000', '$27,000,000', '$16,000,000', '$3,000,000', '$15,000,000', '$25,000,000', '$34,000,000', '$10,000,000', '$20,000,000', '$15,000,000', '$12,000,000', '$5,000,000', '$7,000,000', '$14,000,000', '$15,000,000', '$12,000,000', '$28,300,000', '$8,000,000', '$7,500,000', '$17,000,000', '$5,000,000', '$9,000,000', '$15,000,000', '$22,000,000', '$5,000,000', '$4,500,000', '$4,500,000', '$8,000,000', '$16,000,000', '$8,200,000', '$28,000,000']


len(pg_cost)

67


pg_name = []
for i in pg_index:
        pg_name.append(Drama_DataFrame.Movie[i])
print(pg_name) #showing the pg_name list

['Hugo', 'Dolphin Tale', 'Extraordinary Measures', 'Wonder', 'The Last Song', 'War Room', 'The Lunchbox', 'Somewhere in Time', 'Urban Cowboy', 'Cinderella', 'War Room', 'Wonder', 'Little Women', 'Overcomer', 'The Jazz Singer', 'Cattle Annie and Little Britches', 'The Majestic', 'A Walk to Remember', 'Tuck Everlasting', 'Dreamer', 'The Lake House', 'We Are Marshall', 'Akeelah and the Bee', 'The Ultimate Gift', 'Bridge to Terabithia', 'August Rush', 'Fireproof', 'The Last Song', 'What If...', "God's Not Dead", "Mr. Holland's Opus", 'The Indian in the Cupboard', 'Fluke', 'Three Wishes', 'Phenomenon', 'Contact', 'The Spanish Prisoner', 'Music of the Heart', 'Sense and Sensibility', 'The Secret of Roan Inish', 'The Remains of the Day', 'Gettysburg', 'The Age of Innocence', 'Pure Country', 'Forever Young', 'Newsies', 'A River Runs Through It', 'Honeysuckle Rose', 'Resurrection', 'Taps', 'On Golden Pond', 'Absence of Malice', 'Ragtime', 'Looker', 'The Night the Lights Went Out in Georgia', 'Rocky III', 'Tex', 'Six Weeks', 'Five Days One Summer', 'Staying Alive', 'Eddie and the Cruisers', 'Tender Mercies', 'Testament', 'Table for Five', 'Man, Woman and Child', 'Footloose', 'The Natural']


len(pg_name)

67


pg_return_on_investment = []
for i in pg_index:
        pg_return_on_investment.append(Drama_DataFrame.Profit_x[i])
print(pg_return_on_investment) #showing the pg_return_on_investment list

['$47,784', '$59,068,724', '$-15,173,016', '$284,604,712', '$72,678,948', '$70,975,239', '$10,531,500', '$4,609,597', '$36,918,287', '$447,351,353', '$70,986,904', '$285,937,718', '$176,601,214', '$33,102,988', '$26,696,000', '$-4,565,184', '$-34,693,666', '$35,694,916', '$4,344,615', '$6,741,732', '$74,830,111', '$-21,454,636', '$10,948,425', '$-5,561,265', '$120,587,063', '$34,605,762', '$32,973,297', '$69,137,047', '$-2,473,712', '$62,667,874', '$83,269,971', '$-9,343,870', '$-11,012,232', '$-2,974,504', '$120,036,382', '$81,120,329', '$3,835,130', '$-12,140,606', '$118,582,776', '$3,101,815', '$48,954,968', '$-14,230,040', '$-1,744,560', '$5,164,458', '$107,956,187', '$-12,180,515', '$31,440,294', '$12,815,212', '$150,297,525', '$21,856,053', '$104,285,432', '$28,716,963', '$-13,379,219', '$-4,718,768', '$7,423,752', '$108,052,686', '$544,368,315', '$-2,331,975', '$-14,800,922', '$42,892,670', '$-213,211', '$3,943,124', '$-2,455,108', '$-5,600,000', '$-14,294,092', '$71,808,942', '$20,000,000']


len(pg_return_on_investment)

67


pg_rating = []
for i in pg_index:
        pg_rating.append(Drama_DataFrame.Averagerating[i])
print(pg_rating) #showing the pg_rating list

[7.5, 6.9, 6.5, 8.0, 6.0, 6.5, 7.8, 7.2, 6.4, 6.9, 6.5, 8.0, 7.8, 6.6, 5.9, 6.1, 6.9, 7.3, 6.6, 6.8, 6.8, 7.1, 7.4, 7.3, 7.1, 7.5, 6.5, 6.0, 6.4, 4.7, 7.3, 6.0, 6.7, 6.1, 6.4, 7.5, 7.2, 6.8, 7.7, 7.5, 7.8, 7.6, 7.2, 7.0, 6.3, 6.9, 7.2, 6.3, 7.3, 6.8, 7.6, 6.9, 7.3, 6.1, 6.0, 6.8, 6.5, 5.7, 6.1, 4.7, 6.9, 7.4, 7.0, 6.1, 6.1, 6.6, 7.5]


len(pg_rating)

67


pg_percent_profit = []
for i in pg_index:
    i = (Drama_DataFrame.Profit[i] / Drama_DataFrame.Production_Budget[i])*100
    pg_percent_profit.append(int(round(i,0)))
print(pg_percent_profit) #showing the pg_percent_profit list

[0, 160, -49, 1423, 363, 2366, 620, 90, 369, 471, 2366, 1430, 442, 662, 6326, -90, -48, 302, 29, 21, 187, -33, 137, -62, 709, 115, 6595, 346, -22, 3133, 362, -21, -73, -30, 375, 90, 38, -45, 741, 103, 326, -57, -5, 52, 540, -81, 262, 256, 2147, 156, 695, 239, -47, -59, 99, 636, 10887, -26, -99, 195, -4, 88, -55, -70, -89, 876, 71]


len(pg_percent_profit)

67


pg_roi_percent = []
for i in pg_percent_profit:
    pg_roi_percent.append("{:}%".format(i))
print(pg_roi_percent) #showing the pg_roi_percent list

['0%', '160%', '-49%', '1423%', '363%', '2366%', '620%', '90%', '369%', '471%', '2366%', '1430%', '442%', '662%', '6326%', '-90%', '-48%', '302%', '29%', '21%', '187%', '-33%', '137%', '-62%', '709%', '115%', '6595%', '346%', '-22%', '3133%', '362%', '-21%', '-73%', '-30%', '375%', '90%', '38%', '-45%', '741%', '103%', '326%', '-57%', '-5%', '52%', '540%', '-81%', '262%', '256%', '2147%', '156%', '695%', '239%', '-47%', '-59%', '99%', '636%', '10887%', '-26%', '-99%', '195%', '-4%', '88%', '-55%', '-70%', '-89%', '876%', '71%']


len(pg_roi_percent)

67


pg_stars = []
for i in pg_rating:
    pg_stars.append('*'*int(i))
print(pg_stars) #showing the pg_stars list

['*******', '******', '******', '********', '******', '******', '*******', '*******', '******', '******', '******', '********', '*******', '******', '*****', '******', '******', '*******', '******', '******', '******', '*******', '*******', '*******', '*******', '*******', '******', '******', '******', '****', '*******', '******', '******', '******', '******', '*******', '*******', '******', '*******', '*******', '*******', '*******', '*******', '*******', '******', '******', '*******', '******', '*******', '******', '*******', '******', '*******', '******', '******', '******', '******', '*****', '******', '****', '******', '*******', '*******', '******', '******', '******', '*******']


len(pg_stars)

67


system_rating_pg = pd.DataFrame({"Name of Movie":pg_name, "Cost":pg_cost, 
                                "Return On Investment":pg_return_on_investment, 
                                "ROI Percentage":pg_roi_percent,"Ratings":pg_stars})


system_rating_pg


neg_values = []
for i,x in enumerate(pg_percent_profit): 
    if x <= 0: neg_values.append(i)
print(neg_values) #showing the neg_values list

[0, 2, 15, 16, 21, 23, 28, 31, 32, 33, 37, 41, 42, 45, 52, 53, 57, 58, 60, 62, 63, 64]


len(neg_values)

22


system_rating_pg = system_rating_pg.drop(labels=neg_values, axis=0)
system_rating_pg = system_rating_pg.reset_index(drop=True)


system_rating_pg


system_rating_pg1=system_rating_pg[:22]
system_rating_pg1


system_rating_pg2=system_rating_pg[22:]
system_rating_pg2


pg_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_pg['Cost']]) / len(system_rating_pg['Cost'])


pg_avg_value

18060488.888888888


pg_cost_index = [int(i.replace('$', '').replace(',', ''))for i in system_rating_pg['Cost']]
#below ayg
pg_below_avg5 = []
for i,x in enumerate(pg_cost_index):
    if x <= 18060488:pg_below_avg5.append(i)
    
pg_below_avg6 = []
for i,x in enumerate(pg_cost_index):
    if x >= 18060488:pg_below_avg6.append(i)


print(pg_below_avg5)

[3, 4, 5, 6, 8, 11, 12, 13, 14, 17, 18, 20, 22, 26, 27, 28, 29, 30, 32, 33, 34, 35, 36, 37, 38, 39, 40, 42, 43]


print(pg_below_avg6)

[0, 1, 2, 7, 9, 10, 15, 16, 19, 21, 23, 24, 25, 31, 41, 44]


pg_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_pg['Return On Investment']]) / len(system_rating_pg['Cost'])


pg_avg_value

83389266.8888889


pg_roi_index = [int(i.replace('$', '').replace(',', ''))for i in system_rating_pg['Return On Investment']]
#below ayg
pg_below_avg7 = []
for i,x in enumerate(pg_roi_index):
    if x <= 83389266:pg_below_avg7.append(i)
    
pg_below_avg8 = []
for i,x in enumerate(pg_roi_index):
    if x >= 83389266:pg_below_avg8.append(i)


print(pg_below_avg7)

[0, 2, 3, 4, 5, 6, 8, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 25, 26, 28, 29, 30, 32, 33, 35, 37, 38, 41, 42, 43, 44]


print(pg_below_avg8)

[1, 7, 9, 10, 18, 24, 27, 31, 34, 36, 39, 40]


pg_avg_value = sum([int(i.replace('%', ''))
                 for i in system_rating_pg['ROI Percentage']]) / len(system_rating_pg['Cost'])


pg_avg_value

1064.3555555555556


roi_percent_index_pg = [int(i.replace('%', ''))for i in system_rating_pg['ROI Percentage']]
#below ayg
pg_above_avg = []
for i,x in enumerate(roi_percent_index_pg):
    if x >= 1064:pg_above_avg.append(i)


print(pg_above_avg)

[1, 3, 8, 9, 12, 20, 22, 34, 40]


def Ratings35(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(22):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight36(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(22):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#FA5F55;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
        df.iloc[i,1] = 'font-size:4pt'
    return df 


def highlight_cells37(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg_below_avg5[:12]:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom:2px solid black'
    return df 

def highlight_cells38(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg_below_avg6[:10]:
        df.iloc[i,1] = 'background-color:#FA5F55;color:white;border-bottom:2px solid black'
    return df 

def highlight_cells39(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg_below_avg7[:17]:
        df.iloc[i,2] = 'background-color:#FA5F55;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells40(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg_below_avg8[:5]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells41(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg_above_avg[:6]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 


def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_pg1=system_rating_pg1.style.apply(Ratings_highlight36, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #FA5F55')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#FA5F55")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#FA5F55')]}#index
                         ])\
            .apply(Ratings35, axis=None)\
            .apply(highlight_cells37, axis=None)\
            .apply(highlight_cells38, axis=None)\
            .apply(highlight_cells39, axis=None)\
            .apply(highlight_cells40, axis=None)\
            .apply(highlight_cells41, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


def Ratings41(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(23):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight42(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(23):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#FA5F55;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
        df.iloc[i,1] = 'font-size:4pt'
    return df 


def highlight_cells43(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [1, 2, 3, 9, 19, 22]:
        df.iloc[i,1] = 'background-color:#FA5F55;color:white;border-bottom:2px solid black'
    return df 

def highlight_cells44(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21]:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom:2px solid black'
    return df 

def highlight_cells45(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 3, 4, 6, 7, 8, 10, 11, 13, 15, 16, 18, 19, 20, 21, 22]:
        df.iloc[i,2] = 'background-color:#FA5F55;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells46(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [1, 2, 5, 9, 12, 14, 17]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells47(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 12, 18]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 


def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_pg2 = system_rating_pg2.style.apply(Ratings_highlight42, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #FA5F55')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#FA5F55")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#FA5F55')]}#index
                         ])\
            .apply(Ratings41, axis=None)\
            .apply(highlight_cells43, axis=None)\
            .apply(highlight_cells44, axis=None)\
            .apply(highlight_cells45, axis=None)\
            .apply(highlight_cells46, axis=None)\
            .apply(highlight_cells47, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


dfi.export(system_rating_pg1, 'system_rating_pg1.png')


dfi.export(system_rating_pg2, 'system_rating_pg2.png')


def display_side_by_side3(*args):
    html_str = "<center><font size=6 style='color:#FA5F55'>The Return On Investement on PG-rated Movies.</font></center> <br>  " 
 
    for df in args:
        html_str += df.to_html()
    display_html(
        html_str.replace('table','table style="display:inline"'), 
        raw=True
    )


pg13_index = []
for i,x in enumerate(Drama_DataFrame.Rating):
    if x == 'PG-13':pg13_index.append(i)
print(pg13_index) #showing the pg13_index list

[2, 4, 7, 8, 12, 15, 16, 17, 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 30, 32, 33, 34, 35, 37, 38, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 54, 60, 63, 65, 68, 69, 70, 72, 73, 74, 75, 78, 79, 80, 83, 86, 89, 91, 95, 96, 99, 100, 102, 104, 105, 108, 109, 113, 114, 115, 117, 119, 122, 123, 131, 132, 143, 149, 151]


len(pg13_index)

76


pg13_profit = []
for i in pg13_index:
        pg13_profit.append(Drama_DataFrame.Profit[i])
print(pg13_profit) #showing the pg13_profit list

[583698673.0, 559454789.0, 77551594.0, -12181087.0, 35552675.0, 163591522.0, 129748880.0, 58660270.0, -8357834.0, -23612961.0, 22004627.0, 156127894.0, 4478084.0, 122498338.0, 129590606.0, -23659233.0, -8875633.0, 78809717.0, 136567581.0, 60143987.0, 49309093.0, 217276928.0, 26721826.0, 29802928.0, 132552290.0, 167618160.0, 38984536.0, -13518595.0, 66050951.0, -11684491.0, 15059418.0, 188120004.0, 117033509.0, 71633833.0, 41540205.0, 4847480.0, 57917283.0, 40282881.0, -15953962.0, 188265198.0, 2281732.0, 57086711.0, -3810190.0, -10319750.0, 317522294.0, 21028230.0, 36545707.0, 40506120.0, 113955898.0, 5601987.0, 44168692.0, 20044909.0, 20069303.0, 20909437.0, 11477345.0, 67356170.0, 51076141.0, 51603136.0, 21556959.0, 27087044.0, 72831866.0, 12971021.0, 23787727.0, 29964656.0, 10369708.0, 143806510.0, 36699612.0, 13945682.0, 1205034.0, -3472240.0, -3157373.0, 12698355.0, 33185884.0, 4152584.0, 3478400.0, 1927779.0]


len(pg13_profit)

76


pg13_cost = []
for i in pg13_index:
        pg13_cost.append(Drama_DataFrame.Production_Budget_x[i])
print(pg13_cost) #showing the pg13_cost list

['$110,000,000', '$75,000,000', '$60,000,000', '$60,000,000', '$55,000,000', '$50,000,000', '$50,000,000', '$50,000,000', '$50,000,000', '$50,000,000', '$49,000,000', '$47,000,000', '$44,000,000', '$40,000,000', '$40,000,000', '$40,000,000', '$40,000,000', '$38,000,000', '$37,000,000', '$37,000,000', '$36,000,000', '$35,000,000', '$35,000,000', '$34,000,000', '$33,000,000', '$30,000,000', '$30,000,000', '$30,000,000', '$28,000,000', '$27,500,000', '$26,000,000', '$25,000,000', '$25,000,000', '$25,000,000', '$25,000,000', '$25,000,000', '$25,000,000', '$24,000,000', '$21,000,000', '$20,000,000', '$20,000,000', '$19,000,000', '$18,000,000', '$18,000,000', '$17,000,000', '$17,000,000', '$16,000,000', '$16,000,000', '$15,000,000', '$15,000,000', '$15,000,000', '$14,000,000', '$13,000,000', '$12,000,000', '$12,000,000', '$11,000,000', '$11,000,000', '$10,000,000', '$10,000,000', '$9,700,000', '$9,000,000', '$9,000,000', '$7,400,000', '$7,000,000', '$6,000,000', '$5,000,000', '$5,000,000', '$5,000,000', '$5,000,000', '$4,500,000', '$4,357,373', '$2,600,000', '$2,000,000', '$1,400,000', '$250,000', '$175,000']


len(pg13_cost)

76


pg13_name = []
for i in pg13_index:
        pg13_name.append(Drama_DataFrame.Movie[i])
print(pg13_name) #showing the pg13_name list

['Gravity', 'Sing', 'Contagion', 'Trouble with the Curve', 'Burlesque', 'Creed II', 'The Post', 'Hereafter', 'Dream House', 'Upside Down', 'Anna Karenina', 'Arrival', 'Charlie St. Cloud', 'Bridge of Spies', 'The Impossible', 'Paranoia', 'Victor Frankenstein', 'Water for Elephants', 'Creed', 'The Rite', 'Collateral Beauty', 'True Grit', 'The Tree of Life', 'The Longest Ride', 'Step Up Revolution', 'The Vow', 'The Age of Adaline', 'The Space Between Us', 'Safe Haven', 'Anonymous', 'The Best of Me', 'The Help', 'Dear John', 'The Lucky One', 'The Giver', 'Draft Day', 'Rings', 'Fences', 'The Beaver', 'Me Before You', 'The Light Between Oceans', 'The Book Thief', 'Labor Day', 'Midnight Special', 'A Quiet Place', 'Beastly', 'The Roommate', 'Remember Me', 'The Woman in Black', 'Country Strong', 'One Day', 'Suffragette', 'The Perks of Being a Wallflower', 'Project Almanac', 'Wish Upon', 'If I Stay', 'Brooklyn', 'Everything, Everything', 'Mud', 'Amour', 'Ouija: Origin of Evil', 'Black or White', 'The Bye Bye Man', 'Gifted', 'The Words', 'Lights Out', 'Still Alice', 'Before I Fall', 'Rabbit Hole', 'Maggie', 'Anna', 'Ida', 'Courageous', 'Mustang', 'Like Crazy', 'Another Earth']


len(pg13_name)

76


pg13_return_on_investment = []
for i in pg13_index:
        pg13_return_on_investment.append(Drama_DataFrame.Profit_x[i])
print(pg13_return_on_investment) #showing the pg13_return_on_investment list

['$583,698,673', '$559,454,789', '$77,551,594', '$-12,181,087', '$35,552,675', '$163,591,522', '$129,748,880', '$58,660,270', '$-8,357,834', '$-23,612,961', '$22,004,627', '$156,127,894', '$4,478,084', '$122,498,338', '$129,590,606', '$-23,659,233', '$-8,875,633', '$78,809,717', '$136,567,581', '$60,143,987', '$49,309,093', '$217,276,928', '$26,721,826', '$29,802,928', '$132,552,290', '$167,618,160', '$38,984,536', '$-13,518,595', '$66,050,951', '$-11,684,491', '$15,059,418', '$188,120,004', '$117,033,509', '$71,633,833', '$41,540,205', '$4,847,480', '$57,917,283', '$40,282,881', '$-15,953,962', '$188,265,198', '$2,281,732', '$57,086,711', '$-3,810,190', '$-10,319,750', '$317,522,294', '$21,028,230', '$36,545,707', '$40,506,120', '$113,955,898', '$5,601,987', '$44,168,692', '$20,044,909', '$20,069,303', '$20,909,437', '$11,477,345', '$67,356,170', '$51,076,141', '$51,603,136', '$21,556,959', '$27,087,044', '$72,831,866', '$12,971,021', '$23,787,727', '$29,964,656', '$10,369,708', '$143,806,510', '$36,699,612', '$13,945,682', '$1,205,034', '$-3,472,240', '$-3,157,373', '$12,698,355', '$33,185,884', '$4,152,584', '$3,478,400', '$1,927,779']


len(pg13_return_on_investment)

76


pg13_rating = []
for i in pg13_index:
        pg13_rating.append(Drama_DataFrame.Averagerating[i])
print(pg13_rating) #showing the pg13_rating list

[7.7, 7.1, 6.6, 6.8, 6.4, 7.2, 7.2, 6.5, 6.0, 6.6, 6.6, 7.9, 6.5, 7.6, 7.6, 5.7, 6.0, 6.9, 5.8, 6.0, 6.8, 7.6, 6.8, 7.1, 6.5, 6.8, 7.2, 6.4, 6.7, 6.9, 6.7, 8.1, 6.3, 6.5, 6.5, 6.8, 4.5, 7.2, 6.7, 7.4, 7.2, 7.6, 6.9, 6.6, 6.6, 5.6, 4.9, 7.1, 6.4, 6.3, 7.0, 6.9, 8.0, 6.4, 5.0, 6.8, 7.5, 6.4, 7.4, 7.9, 6.1, 6.6, 4.3, 5.6, 7.1, 6.4, 7.5, 6.4, 7.0, 6.4, 6.5, 7.4, 7.0, 7.6, 6.7, 7.0]


len(pg13_rating)

76


pg13_percent_profit = []
for i in pg13_index:
    i = (Drama_DataFrame.Profit[i] / Drama_DataFrame.Production_Budget[i])*100
    pg13_percent_profit.append(int(round(i,0)))
print(pg13_percent_profit) #showing the pg13_percent_profit list

[531, 746, 129, -20, 65, 327, 259, 117, -17, -47, 45, 332, 10, 306, 324, -59, -22, 207, 369, 163, 137, 621, 76, 88, 402, 559, 130, -45, 236, -42, 58, 752, 468, 287, 166, 19, 232, 168, -76, 941, 11, 300, -21, -57, 1868, 124, 228, 253, 760, 37, 294, 143, 154, 174, 96, 612, 464, 516, 216, 279, 809, 144, 321, 428, 173, 2876, 734, 279, 24, -77, -72, 488, 1659, 297, 1391, 1102]


len(pg13_percent_profit)

76


pg13_roi_percent = []
for i in pg13_percent_profit:
    pg13_roi_percent.append("{:}%".format(i))
print(pg13_roi_percent) #showing the pg13_roi_percent list

['531%', '746%', '129%', '-20%', '65%', '327%', '259%', '117%', '-17%', '-47%', '45%', '332%', '10%', '306%', '324%', '-59%', '-22%', '207%', '369%', '163%', '137%', '621%', '76%', '88%', '402%', '559%', '130%', '-45%', '236%', '-42%', '58%', '752%', '468%', '287%', '166%', '19%', '232%', '168%', '-76%', '941%', '11%', '300%', '-21%', '-57%', '1868%', '124%', '228%', '253%', '760%', '37%', '294%', '143%', '154%', '174%', '96%', '612%', '464%', '516%', '216%', '279%', '809%', '144%', '321%', '428%', '173%', '2876%', '734%', '279%', '24%', '-77%', '-72%', '488%', '1659%', '297%', '1391%', '1102%']


len(pg13_roi_percent)

76


pg13_stars = []
for i in pg13_rating:
    pg13_stars.append('*'*int(i))
print(pg13_stars) #showing the pg13_stars list

['*******', '*******', '******', '******', '******', '*******', '*******', '******', '******', '******', '******', '*******', '******', '*******', '*******', '*****', '******', '******', '*****', '******', '******', '*******', '******', '*******', '******', '******', '*******', '******', '******', '******', '******', '********', '******', '******', '******', '******', '****', '*******', '******', '*******', '*******', '*******', '******', '******', '******', '*****', '****', '*******', '******', '******', '*******', '******', '********', '******', '*****', '******', '*******', '******', '*******', '*******', '******', '******', '****', '*****', '*******', '******', '*******', '******', '*******', '******', '******', '*******', '*******', '*******', '******', '*******']


len(pg13_stars)

76


system_rating_pg13 = pd.DataFrame({"Name of Movie":pg13_name, "Cost":pg13_cost, 
                                "Return On Investment":pg13_return_on_investment, 
                                "ROI Percentage":pg13_roi_percent,"Ratings":pg13_stars})


system_rating_pg13


neg_values = []
for i,x in enumerate(pg13_percent_profit): 
    if x <= 0: neg_values.append(i)
print(neg_values) #showing the neg_values list

[3, 8, 9, 15, 16, 27, 29, 38, 42, 43, 69, 70]


len(neg_values)

12


system_rating_pg13= system_rating_pg13.drop(labels=neg_values, axis=0)
system_rating_pg13 = system_rating_pg13.reset_index(drop=True)


system_rating_pg13


system_rating_pg131=system_rating_pg13[:22]
system_rating_pg131


system_rating_pg132=system_rating_pg13[22:42]
system_rating_pg132


system_rating_pg133=system_rating_pg13[42:]
system_rating_pg133


pg13_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_pg13['Cost']]) / len(system_rating_pg13['Cost'])


pg13_avg_value

24695703.125


pg13_cost_index = [int(i.replace('$', '').replace(',', ''))
                   for i in system_rating_pg13['Cost']]
#below ayg
pg13_below_avg1 = []
for i,x in enumerate(pg13_cost_index):
    if x <= 24695703:pg13_below_avg1.append(i)
    
pg13_below_avg2 = []
for i,x in enumerate(pg13_cost_index):
    if x >= 24695703:pg13_below_avg2.append(i)


print(pg13_below_avg1)

[30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63]


print(pg13_below_avg2)

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29]


pg13_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                for i in system_rating_pg13['Return On Investment']]) / len(system_rating_pg13['Cost'])


pg13_avg_value

79724974.890625


pg13_roi_index = [int(i.replace('$', '').replace(',', ''))
                  for i in system_rating_pg13['Return On Investment']]
#below ayg
pg13_below_avg3 = []
for i,x in enumerate(pg13_roi_index):
    if x <= 79724974:pg13_below_avg3.append(i)
    
pg13_below_avg4 = []
for i,x in enumerate(pg13_roi_index):
    if x >= 79724974:pg13_below_avg4.append(i)


print(pg13_below_avg3)

[2, 3, 6, 7, 9, 12, 14, 15, 17, 18, 21, 22, 23, 26, 27, 28, 29, 30, 32, 33, 35, 36, 37, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63]


print(pg13_below_avg4)

[0, 1, 4, 5, 8, 10, 11, 13, 16, 19, 20, 24, 25, 31, 34, 38, 55]


pg13_avg_value = sum([int(i.replace('%', ''))
                 for i in system_rating_pg13['ROI Percentage']]) / len(system_rating_pg13['Cost'])


pg13_avg_value

414.4375


roi_percent_index_pg13 = [int(i.replace('%', ''))
                          for i in system_rating_pg13['ROI Percentage']]
#below ayg
pg13_above_avg = []
for i,x in enumerate(roi_percent_index_pg13):
    if x >= 414:pg13_above_avg.append(i)


print(pg13_above_avg)

[0, 1, 16, 20, 24, 25, 31, 34, 38, 45, 46, 47, 50, 53, 55, 56, 59, 60, 62, 63]


def Ratings48(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(22):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight49(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(22):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#DE3163;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
        df.iloc[i,1] = 'font-size:4pt'
    return df 


def highlight_cells50(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg13_below_avg1:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom:2px solid black'
    return df 

def highlight_cells51(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg13_below_avg2[:22]:
        df.iloc[i,1] = 'background-color:#DE3163;color:white;border-bottom:2px solid black'
    return df 

def highlight_cells52(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg13_below_avg3[:11]:
        df.iloc[i,2] = 'background-color:#DE3163;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells53(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg13_below_avg4[:11]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells54(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg13_above_avg[:4]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 


def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_pg131=system_rating_pg131.style.apply(Ratings_highlight49, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #DE3163')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#DE3163")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#DE3163')]}#index
                         ])\
            .apply(Ratings48, axis=None)\
            .apply(highlight_cells51, axis=None)\
            .apply(highlight_cells52, axis=None)\
            .apply(highlight_cells53, axis=None)\
            .apply(highlight_cells54, axis=None)\
            #.apply(highlight_cells50, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


def Ratings48(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(20):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight49(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(20):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#DE3163;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
        df.iloc[i,1] = 'font-size:4pt'
    return df 


def highlight_cells50(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(8,20):
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom:2px solid black'
    return df 

def highlight_cells51(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(8):
        df.iloc[i,1] = 'background-color:#DE3163;color:white;border-bottom:2px solid black'
    return df 

def highlight_cells52(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 1, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 17, 18, 19]:
        df.iloc[i,2] = 'background-color:#DE3163;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells53(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [2, 3, 9, 16, 12]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells54(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [2, 3, 9, 16, 12]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 


def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_pg132=system_rating_pg132.style.apply(Ratings_highlight49, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #DE3163')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#DE3163")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#DE3163')]}#index
                         ])\
            .apply(Ratings48, axis=None)\
            .apply(highlight_cells51, axis=None)\
            .apply(highlight_cells52, axis=None)\
            .apply(highlight_cells53, axis=None)\
            .apply(highlight_cells54, axis=None)\
            .apply(highlight_cells50, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


def Ratings48(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(22):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight49(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(22):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#DE3163;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
        df.iloc[i,1] = 'font-size:4pt'
    return df 


def highlight_cells50(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(22):
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom:2px solid black'
    return df 

def highlight_cells51(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in pg13_below_avg2[:22]:
        df.iloc[i,1] = 'background-color:#DE3163;color:white;border-bottom:2px solid black'
    return df 

def highlight_cells52(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21]:
        df.iloc[i,2] = 'background-color:#DE3163;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells53(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[11,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells54(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [3, 4, 5, 8, 11, 13, 14, 17, 18, 20, 21 ]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 


def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_pg133 = system_rating_pg133.style.apply(Ratings_highlight49, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #DE3163')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#DE3163")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#DE3163')]}#index
                         ])\
            .apply(Ratings48, axis=None)\
            .apply(highlight_cells50, axis=None)\
            .apply(highlight_cells52, axis=None)\
            .apply(highlight_cells53, axis=None)\
            .apply(highlight_cells54, axis=None)\
           
            #.apply(highlight_cells51, axis=None)\
            
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


dfi.export(system_rating_pg131, 'system_rating_pg131.png')


dfi.export(system_rating_pg132, 'system_rating_pg132.png')


dfi.export(system_rating_pg133, 'system_rating_pg133.png')


def display_side_by_side4(*args):
    html_str = "<center><font size=6 style='color:#DE3163'>The Return On Investement on PG13-rated Movies.</font></center> <br>  " 
 
    for df in args:
        html_str += df.to_html()
    display_html(
        html_str.replace('table','table style="display:inline"'), 
        raw=True
    )


nc17_index = []
for i,x in enumerate(Drama_DataFrame.Rating):
    if x == 'NC-17':nc17_index.append(i)
print(nc17_index) #showing the nc17_index list

[112, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305]


len(nc17_index)

49


nc17_profit = []
for i in nc17_index:
        nc17_profit.append(Drama_DataFrame.Profit[i])
print(nc17_profit) #showing the nc17_profit list

[13912841.0, 4856268.0, 8404.0, 257845.0, 659312.0, 18912216.0, -24649246.0, 89410061.0, -4503941.0, 121165.0, -1712236.0, 52091915.0, 13912841.0, 15465835.0, -7249246.0, 307113.0, 13912841.0, 15390895.0, 15566240.0, 1315026.0, 256669.0, 201120004.0, -5340890.0, 50167430.0, -17763156.0, 2311944.0, -794431.0, 13912841.0, -2605698.0, 2548651.0, -216465.0, -596907.0, 16283563.0, 3664240.0, 1038916.0, -2509128.0, 8000000.0, 18912216.0, 94673038.0, 34897711.0, 401802.0, 50167430.0, 3546453.0, -672713.0, -13085834.0, -3838180.0, 958404.0, -2237424.0, 858737.0]


len(nc17_profit)

49


nc17_cost = []
for i in nc17_index:
        nc17_cost.append(Drama_DataFrame.Production_Budget_x[i])
print(nc17_cost) #showing the nc17_cost list

['$6,500,000', '$12,500,000', '$1,000,000', '$20,000', '$955,472', '$1,500,000', '$45,000,000', '$9,000,000', '$5,000,000', '$15,000,000', '$2,734,384', '$15,000,000', '$6,500,000', '$4,000,000', '$45,000,000', '$15,000,000', '$6,500,000', '$4,074,940', '$1,000,000', '$1,000,000', '$3,565,572', '$12,000,000', '$10,000,000', '$15,000,000', '$19,000,000', '$350,000', '$1,000,000', '$6,500,000', '$4,700,000', '$904,765', '$3,000,000', '$700,000', '$34,000,000', '$230,000', '$1,000,000', '$3,200,000', '$1,000,000', '$1,500,000', '$6,500,000', '$1,250,000', '$12,000', '$15,000,000', '$2,200,000', '$1,300,000', '$15,000,000', '$6,400,000', '$50,000', '$3,259,572', '$612,072']


len(nc17_cost)

49


nc17_name = []
for i in nc17_index:
        nc17_name.append(Drama_DataFrame.Movie[i])
print(nc17_name) #showing the nc17_name list

['Shame', 'Matador', 'Whore', 'Tokyo Decadence', 'Wide Sargasso Sea', 'Kids', 'Showgirls', 'Crash', 'Bent', 'The Dreamers', 'Ma mère', 'Lust, Caution', 'Shame', 'Blue Is the Warmest Colour', 'Showgirls', 'The Dreamers', 'Shame', 'Blue Is the Warmest Colour', 'Blue Valentine', 'Two Girls and a Guy', 'Elles', 'Hell', 'Killer Joe', 'Se, jie', 'Queen of Hearts', 'The Evil Dead', 'Man Bites Dog', 'Shame', 'Nymphomaniac: Vol. I', 'Arabian Nights', 'Frontier(s)', 'Chained', 'Natural Born Killers', 'Clerks', 'Bad Lieutenant', 'The Big Feast', 'Beyond the Valley of the Dolls', 'Kids', 'Crash', 'Last Tango in Paris', 'Pink Flamingos', 'Lust, Caution ', 'Happiness 1998', 'Orgazmo', 'A Dirty Shame', 'Young Adam', 'Whore 1991', 'Ma Mère', 'Law of Desire']


len(nc17_name)

49


nc17_return_on_investment = []
for i in nc17_index:
        nc17_return_on_investment.append(Drama_DataFrame.Profit_x[i])
print(nc17_return_on_investment) #showing the nc17_return_on_investment list

['$13,912,841', '$4,856,268', '$8,404', '$257,845', '$659,312', '$18,912,216', '$-24,649,246', '$89,410,061', '$-4,503,941', '$121,165', '$-1,712,236', '$52,091,915', '$13,912,841', '$15,465,835', '$-7,249,246', '$307,113', '$13,912,841', '$15,390,895', '$15,566,240', '$1,315,026', '$256,669', '$201,120,004', '$-5,340,890', '$50,167,430', '$-17,763,156', '$2,311,944', '$-794,431', '$13,912,841', '$-2,605,698', '$2,548,651', '$-216,465', '$-596,907', '$16,283,563', '$3,664,240', '$1,038,916', '$-2,509,128', '$8,000,000', '$18,912,216', '$94,673,038', '$34,897,711', '$401,802', '$50,167,430', '$3,546,453', '$-672,713', '$-13,085,834', '$-3,838,180', '$958,404', '$-2,237,424', '$858,737']


len(nc17_return_on_investment)

49


nc17_rating = []
for i in nc17_index:
        nc17_rating.append(Drama_DataFrame.Averagerating[i])
print(nc17_rating) #showing the nc17_rating list

[7.2, 7.0, 5.6, 6.0, 5.7, 7.1, 4.9, 6.4, 7.2, 7.2, 5.1, 7.5, 7.2, 7.7, 4.9, 7.1, 7.2, 7.7, 7.4, 5.5, 5.6, 5.9, 6.7, 7.5, 7.1, 7.4, 7.4, 7.2, 6.9, 6.7, 6.2, 6.4, 7.2, 7.7, 7.0, 6.2, 6.1, 7.0, 7.8, 6.9, 6.0, 7.5, 7.7, 6.1, 5.1, 6.4, 5.5, 5.0, 7.1]


len(nc17_rating)

49


nc17_percent_profit = []
for i in nc17_index:
    i = (Drama_DataFrame.Profit[i] / Drama_DataFrame.Production_Budget[i])*100
    nc17_percent_profit.append(int(round(i,0)))
print(nc17_percent_profit) #showing the nc17_percent_profit list

[214, 39, 1, 1289, 69, 1261, -55, 993, -90, 1, -63, 347, 214, 387, -16, 2, 214, 378, 1557, 132, 7, 1676, -53, 334, -93, 661, -79, 214, -55, 282, -7, -85, 48, 1593, 104, -78, 800, 1261, 1457, 2792, 3348, 334, 161, -52, -87, -60, 1917, -69, 140]


len(nc17_percent_profit)

49


nc17_roi_percent = []
for i in nc17_percent_profit:
    nc17_roi_percent.append("{:}%".format(i))
print(nc17_roi_percent) #showing the nc17_roi_percent list

['214%', '39%', '1%', '1289%', '69%', '1261%', '-55%', '993%', '-90%', '1%', '-63%', '347%', '214%', '387%', '-16%', '2%', '214%', '378%', '1557%', '132%', '7%', '1676%', '-53%', '334%', '-93%', '661%', '-79%', '214%', '-55%', '282%', '-7%', '-85%', '48%', '1593%', '104%', '-78%', '800%', '1261%', '1457%', '2792%', '3348%', '334%', '161%', '-52%', '-87%', '-60%', '1917%', '-69%', '140%']


len(nc17_roi_percent)

49


nc17_stars = []
for i in nc17_rating:
    nc17_stars.append('*'*int(i))
print(nc17_stars) #showing the nc17_stars list

['*******', '*******', '*****', '******', '*****', '*******', '****', '******', '*******', '*******', '*****', '*******', '*******', '*******', '****', '*******', '*******', '*******', '*******', '*****', '*****', '*****', '******', '*******', '*******', '*******', '*******', '*******', '******', '******', '******', '******', '*******', '*******', '*******', '******', '******', '*******', '*******', '******', '******', '*******', '*******', '******', '*****', '******', '*****', '*****', '*******']


len(nc17_stars)

49


system_rating_nc17 = pd.DataFrame({"Name of Movie":nc17_name, "Cost":nc17_cost, 
                                "Return On Investment":nc17_return_on_investment, 
                                "ROI Percentage":nc17_roi_percent,"Ratings":nc17_stars})


system_rating_nc17


neg_values = []
for i,x in enumerate(nc17_percent_profit): 
    if x <= 0: neg_values.append(i)
print(neg_values) #showing the neg_values list

[6, 8, 10, 14, 22, 24, 26, 28, 30, 31, 35, 43, 44, 45, 47]


len(neg_values)

15


system_rating_nc17 = system_rating_nc17.drop(labels=neg_values, axis=0)
system_rating_nc17 = system_rating_nc17.reset_index(drop=True)


system_rating_nc17


system_rating_nc171=system_rating_nc17[:17]
system_rating_nc171


system_rating_nc172=system_rating_nc17[17:]
system_rating_nc172


nc_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_nc17['Cost']]) / len(system_rating_nc17['Cost'])


nc_avg_value

5918377.088235294


nc_cost_index = [int(i.replace('$', '').replace(',', ''))for i in system_rating_nc17['Cost']]
#below ayg
nc_below_avg1 = []
for i,x in enumerate(nc_cost_index):
    if x <= 5918377:nc_below_avg1.append(i)
    
nc_below_avg2 = []
for i,x in enumerate(nc_cost_index):
    if x >= 5918377:nc_below_avg2.append(i)


print(nc_below_avg1)

[2, 3, 4, 5, 10, 13, 14, 15, 16, 19, 21, 23, 24, 25, 26, 28, 29, 31, 32, 33]


print(nc_below_avg2)

[0, 1, 6, 7, 8, 9, 11, 12, 17, 18, 20, 22, 27, 30]


nc_avg_value = sum([int(i.replace('$', '').replace(',', ''))
                 for i in system_rating_nc17['Return On Investment']]) / len(system_rating_nc17['Cost'])


nc_avg_value

22347672.55882353


nc_roi_index = [int(i.replace('$', '').replace(',', ''))
                for i in system_rating_nc17['Return On Investment']]
#below ayg
nc_below_avg3 = []
for i,x in enumerate(nc_roi_index):
    if x <= 22347672:nc_below_avg3.append(i)
    
nc_below_avg4 = []
for i,x in enumerate(nc_roi_index):
    if x >= 22347672:nc_below_avg4.append(i)


print(nc_below_avg3)

[0, 1, 2, 3, 4, 5, 7, 9, 10, 11, 12, 13, 14, 15, 16, 19, 20, 21, 22, 23, 24, 25, 26, 29, 31, 32, 33]


print(nc_below_avg4)

[6, 8, 17, 18, 27, 28, 30]


nc_avg_value = sum([int(i.replace('%', ''))
                 for i in system_rating_nc17['ROI Percentage']]) / len(system_rating_nc17['Cost'])


nc_avg_value

712.5588235294117


roi_percent_index_nc = [int(i.replace('%', ''))for i in system_rating_nc17['ROI Percentage']]
#below ayg
nc_above_avg = []
for i,x in enumerate(roi_percent_index_nc):
    if x >= 712:nc_above_avg.append(i)


print(nc_above_avg)

[3, 5, 6, 14, 17, 23, 25, 26, 27, 28, 29, 32]


def Ratings1(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(17):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight2(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(17):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#581845;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
    return df 


def highlight_cells3(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in nc_below_avg1[:9]:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells4(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in nc_below_avg2[:8]:
        df.iloc[i,1] = 'background-color:#581845;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells5(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in nc_below_avg3[:15]:
        df.iloc[i,2] = 'background-color:#581845;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells6(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in nc_below_avg4[:2]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells7(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in nc_above_avg[:4]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 

def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 


system_rating_nc171 = system_rating_nc171.style.apply(Ratings_highlight2, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #581845')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#581845")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#581845')]}
                                                                                 ])\
            .apply(Ratings1, axis=None)\
            .apply(highlight_cells3, axis=None)\
            .apply(highlight_cells4, axis=None)\
            .apply(highlight_cells5, axis=None)\
            .apply(highlight_cells6, axis=None)\
            .apply(highlight_cells7, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 1')


dfi.export(system_rating_nc171, 'system_rating_nc171.png')


def Ratings8(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(17):#range(19,37):
        df.iloc[i,-1] = "font-size : 11pt;font-weight: bold"
        df.iloc[i,-4] = "font-size : 8pt"
    return df 

def Ratings_highlight9(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in range(17):
        df.iloc[i,-1] = 'color:#FFD700;background-color:white'
        df.iloc[i,0] = 'color:#581845;background-color:white;font-size:8pt;font-weight: bold'
        df.iloc[i,2:4] = 'color:black;background-color:white;font-size:8pt'
    return df 

def highlight_cells10(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [2, 3, 4, 6, 7, 8, 9, 11, 12, 14, 15, 16]:
        df.iloc[i,1] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 

def highlight_cells90(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 1, 5, 10, 13]:
        df.iloc[i,1] = 'background-color:#581845;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells11(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [2, 3, 4, 5, 6, 7, 8, 9, 12, 14, 15, 16]:
        df.iloc[i,2] = 'background-color:#581845;color:white;border-bottom: 2px solid black'
    return df 

def highlight_cells12(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 1, 10, 11, 13]:
        df.iloc[i,2] = 'background-color:yellow;color:black;border-bottom: 2px solid black'
    return df 


def highlight_cells13(x):
    df = x.copy()
    df.loc[:,:] = '' 
    for i in [0, 6, 8, 9, 10, 11, 12, 15]:
        df.iloc[i,3] = 'background-color:#16F529;color:black;border-bottom: 2px solid black'
    return df 

def borders(x):
    df = x.copy()
    df.loc[:,:] = '' 
    df.iloc[10:14,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,0] = 'border-right: 6px solid blue'
    df.iloc[14:18,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[11:14,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    df.iloc[15:18,0] = 'border-right: 6px solid blue'
    df.iloc[15:18,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    
    df.iloc[21:23,1:4] = 'border-bottom: 6px solid blue'
    df.iloc[22,0] = 'border-right: 6px solid blue'
    df.iloc[22:23,-2] = 'border-bottom: 6px solid blue;border-right: 6px solid blue'
    return df 

system_rating_nc172 = system_rating_nc172.style.apply(Ratings_highlight9, axis=None)\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid #581845')]},
            {"selector":"thead", 'props':[("background-color","white"),("color","#581845")]},#headinig
            #{'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','#581845')]}#index
                         ])\
            .apply(Ratings8, axis=None)\
            .apply(highlight_cells10, axis=None)\
            .apply(highlight_cells90, axis=None)\
            .apply(highlight_cells11, axis=None)\
            .apply(highlight_cells12, axis=None)\
            .apply(highlight_cells13, axis=None)\
            #.set_table_attributes("style='display:inline'")\
            #.set_caption('Caption table 2')
            #.apply(borders, axis=None)
            #display_html(df1_style._repr_html_() + df2_style._repr_html_(), raw=True)


dfi.export(system_rating_nc172, 'system_rating_nc172.png')


def display_side_by_side5(*args):
    html_str = "<center><font size=6 style='color:#FF2400'>The Return On Investement on NC-17 Rated Movies.</font></center> <br>  " 
 
    for df in args:
        html_str += df.to_html()
    display_html(
        html_str.replace('table','table style="display:inline"'), 
        raw=True
    )


RIO_R = []
for i in r_percent_profit:
        i /= 10
        RIO_R.append(i)
    
RIO_R.sort(reverse=True)
print(RIO_R) #showing the RIO_R list

[267.0, 244.8, 185.2, 155.7, 133.2, 132.7, 108.1, 105.6, 97.0, 85.0, 81.5, 81.3, 80.8, 73.1, 70.7, 67.5, 60.1, 59.3, 57.5, 50.4, 50.1, 46.5, 44.4, 41.8, 41.1, 40.8, 35.0, 26.3, 25.8, 25.0, 23.8, 21.8, 21.6, 19.9, 19.5, 17.9, 15.6, 13.3, 13.2, 8.1, 7.4, 6.5, 5.4, 4.4, 4.1, 4.0, 3.8, 3.6, 3.5, 2.2, 2.1, 1.6, 1.3, 0.5, 0.4, 0.0, -0.5, -0.9, -1.5, -2.0, -2.6, -2.9, -4.4, -4.9, -5.3, -5.7, -5.8, -6.2, -7.3, -7.5, -7.8, -8.1, -8.2, -8.3, -9.5, -9.6, -9.8]


len(RIO_R[:-22])

55


currency_R = []
for i in RIO_R[:-22]:
    currency_R.append("${:,.2f}".format(i))
print(currency_R) #showing the currency_R list

['$267.00', '$244.80', '$185.20', '$155.70', '$133.20', '$132.70', '$108.10', '$105.60', '$97.00', '$85.00', '$81.50', '$81.30', '$80.80', '$73.10', '$70.70', '$67.50', '$60.10', '$59.30', '$57.50', '$50.40', '$50.10', '$46.50', '$44.40', '$41.80', '$41.10', '$40.80', '$35.00', '$26.30', '$25.80', '$25.00', '$23.80', '$21.80', '$21.60', '$19.90', '$19.50', '$17.90', '$15.60', '$13.30', '$13.20', '$8.10', '$7.40', '$6.50', '$5.40', '$4.40', '$4.10', '$4.00', '$3.80', '$3.60', '$3.50', '$2.20', '$2.10', '$1.60', '$1.30', '$0.50', '$0.40']


len(currency_R)

55


avg_R = statistics.mean(RIO_R[:-22])
avg_R

50.88727272727272


np.percentile(RIO_R[:-22], [25,50,75])

array([ 6.95, 26.3 , 71.9 ])


final_name_r = []
reversed_name = []
for x,i in enumerate(r_name):
    reversed_name.append((r_percent_profit[x], i))
reversed_name.sort(reverse = True)
for i in reversed_name[:-22]:
    final_name_r.append(i[1])
print(final_name_r) #showing the final_name_r list

['A Ghost Story', 'Black Swan', 'Ghost Story', 'Blue Valentine', 'Boyhood', 'Fifty Shades of Grey', 'Whiplash', 'The Witch', 'Buried', 'Unsane', 'Manchester by the Sea', 'Ordinary People', 'Fame', 'Silent House', "Winter's Bone", 'Before Midnight', 'Hereditary', 'Fifty Shades Darker', 'Fifty Shades Freed', 'Gone Girl', 'Margin Call', 'The Florida Project', 'Martha Marcy May Marlene', 'Flight', 'Quartet', 'We Are Your Friends', 'Django Unchained', 'Carol', 'Mommy', 'Addicted', 'The Ides of March', 'Sound of My Voice', 'Knock Knock', 'Arbitrage', 'Ex Machina', 'Room', 'Zero Dark Thirty', 'The Debt', 'Melancholia', 'For Colored Girls', 'Endless Love', 'If Beale Street Could Talk', 'We Need to Talk About Kevin', 'Nocturnal Animals', 'Let Me In', 'Priest', 'The Water Diviner', 'Crimson Peak', 'The Master', 'Raggedy Man', 'Zoot Suit', 'Palo Alto', 'Rich and Famous', 'Take Shelter', 'Locke']


len(final_name_r)

55


dataframe_RIO_r = pd.DataFrame({"Name of Movie":final_name_r, 
                                "Money Generated for Every $1 Spent":currency_R})


dataframe_RIO_r


RIO_G = []
for i in g_percent_profit:
    i /= 10
    RIO_G.append(i)
    
RIO_G.sort(reverse=True)
print(RIO_G) #showing the RIO_G list

[3113.5, 339.0, 209.3, 209.2, 162.9, 130.0, 72.0, 60.6, 57.8, 40.4, 37.7, 37.2, 36.5, 33.4, 32.4, 26.7, 26.6, 24.4, 19.1, 16.6, 8.3, 7.7, 6.9, 5.1, 5.0, -2.3, -4.1, -4.1, -5.2, -6.4, -8.0, -8.8, -9.9, -9.9]


len(RIO_G[:-9])

25


currency_G = []
for i in RIO_G[:-9]:
    currency_G.append("${:,.2f}".format(i))
print(currency_G) #showing the currency_G list

['$3,113.50', '$339.00', '$209.30', '$209.20', '$162.90', '$130.00', '$72.00', '$60.60', '$57.80', '$40.40', '$37.70', '$37.20', '$36.50', '$33.40', '$32.40', '$26.70', '$26.60', '$24.40', '$19.10', '$16.60', '$8.30', '$7.70', '$6.90', '$5.10', '$5.00']


len(currency_G)

25


avg_G = statistics.mean(RIO_G[:-9])
avg_G

188.732


np.percentile(RIO_G[:-9], [25,50,75])

array([19.1, 36.5, 72. ])


final_name_g = []
reversed_name = []
for x,i in enumerate(g_name):
    reversed_name.append((g_percent_profit[x], i))
reversed_name.sort(reverse = True)
for i in reversed_name[:-9]:
    final_name_g.append(i[1])
print(final_name_g) #showing the final_name_g list

['Bambi 1942', 'The Sound of Music', 'Beauty and the Beast 1991', 'The Lion King 1994', 'The Secret Garden', 'The Black Stallion', 'Babe', 'Three Cions in the Fountain', 'Lassie Come Home', 'The Ten Commandments 1966', "Hachiko: A Dog's Story", 'Giant', 'The Hunchback of Notre Drame', 'The Quiet Man', 'My Fair Lady 1964', 'The Rookie', 'The Rookie', 'A Sunday in the Country', 'The Little Rascals', 'Prancer', 'Ramona and Beezus', 'Kit Kittredge: An American Girl', "Charlotte's Web", 'The Tale of Despereaux', 'Pollyanna']


len(final_name_g)

25


dataframe_RIO_g = pd.DataFrame({"Name of Movie":final_name_g, 
                                "Money Generated for Every $1 Spent":currency_G})


dataframe_RIO_g


RIO_PG = []
for i in pg_percent_profit:
    i /= 10
    RIO_PG.append(i)
    
RIO_PG.sort(reverse=True)
print(RIO_PG) #showing the RIO_PG list

[1088.7, 659.5, 632.6, 313.3, 236.6, 236.6, 214.7, 143.0, 142.3, 87.6, 74.1, 70.9, 69.5, 66.2, 63.6, 62.0, 54.0, 47.1, 44.2, 37.5, 36.9, 36.3, 36.2, 34.6, 32.6, 30.2, 26.2, 25.6, 23.9, 19.5, 18.7, 16.0, 15.6, 13.7, 11.5, 10.3, 9.9, 9.0, 9.0, 8.8, 7.1, 5.2, 3.8, 2.9, 2.1, 0.0, -0.4, -0.5, -2.1, -2.2, -2.6, -3.0, -3.3, -4.5, -4.7, -4.8, -4.9, -5.5, -5.7, -5.9, -6.2, -7.0, -7.3, -8.1, -8.9, -9.0, -9.9]


len(RIO_PG[:-22])

45


currency_PG = []
for i in RIO_PG[:-22]:
    currency_PG.append("${:,.2f}".format(i))
print(currency_PG) #showing the currency_PG list

['$1,088.70', '$659.50', '$632.60', '$313.30', '$236.60', '$236.60', '$214.70', '$143.00', '$142.30', '$87.60', '$74.10', '$70.90', '$69.50', '$66.20', '$63.60', '$62.00', '$54.00', '$47.10', '$44.20', '$37.50', '$36.90', '$36.30', '$36.20', '$34.60', '$32.60', '$30.20', '$26.20', '$25.60', '$23.90', '$19.50', '$18.70', '$16.00', '$15.60', '$13.70', '$11.50', '$10.30', '$9.90', '$9.00', '$9.00', '$8.80', '$7.10', '$5.20', '$3.80', '$2.90', '$2.10']


len(currency_PG)

45


avg_PG = statistics.mean(RIO_PG[:-22])
avg_PG

106.43555555555555


np.percentile(RIO_PG[:-22], [25,50,75])

array([13.7, 36.2, 70.9])


final_name_pg = []
reversed_name = []
for x,i in enumerate(pg_name):
    reversed_name.append((pg_percent_profit[x], i))
reversed_name.sort(reverse = True)
for i in reversed_name[:-22]:
    final_name_pg.append(i[1])
print(final_name_pg) #showing the final_name_pg list

['Tex', 'Fireproof', 'The Jazz Singer', "God's Not Dead", 'War Room', 'War Room', 'Resurrection', 'Wonder', 'Wonder', 'Footloose', 'Sense and Sensibility', 'Bridge to Terabithia', 'On Golden Pond', 'Overcomer', 'Rocky III', 'The Lunchbox', 'Forever Young', 'Cinderella', 'Little Women', 'Phenomenon', 'Urban Cowboy', 'The Last Song', "Mr. Holland's Opus", 'The Last Song', 'The Remains of the Day', 'A Walk to Remember', 'A River Runs Through It', 'Honeysuckle Rose', 'Absence of Malice', 'Staying Alive', 'The Lake House', 'Dolphin Tale', 'Taps', 'Akeelah and the Bee', 'August Rush', 'The Secret of Roan Inish', 'The Night the Lights Went Out in Georgia', 'Somewhere in Time', 'Contact', 'Tender Mercies', 'The Natural', 'Pure Country', 'The Spanish Prisoner', 'Tuck Everlasting', 'Dreamer']


len(final_name_pg)

45


dataframe_RIO_pg = pd.DataFrame({"Name of Movie":final_name_pg, 
                                 "Money Generated for Every $1 Spent":currency_PG})


dataframe_RIO_pg


RIO_PG13 = []
for i in pg13_percent_profit:
    i /= 10
    RIO_PG13.append(i)
    
RIO_PG13.sort(reverse=True)
print(RIO_PG13) #showing the RIO_PG13 list

[287.6, 186.8, 165.9, 139.1, 110.2, 94.1, 80.9, 76.0, 75.2, 74.6, 73.4, 62.1, 61.2, 55.9, 53.1, 51.6, 48.8, 46.8, 46.4, 42.8, 40.2, 36.9, 33.2, 32.7, 32.4, 32.1, 30.6, 30.0, 29.7, 29.4, 28.7, 27.9, 27.9, 25.9, 25.3, 23.6, 23.2, 22.8, 21.6, 20.7, 17.4, 17.3, 16.8, 16.6, 16.3, 15.4, 14.4, 14.3, 13.7, 13.0, 12.9, 12.4, 11.7, 9.6, 8.8, 7.6, 6.5, 5.8, 4.5, 3.7, 2.4, 1.9, 1.1, 1.0, -1.7, -2.0, -2.1, -2.2, -4.2, -4.5, -4.7, -5.7, -5.9, -7.2, -7.6, -7.7]


len(RIO_PG13[:-12])

64


currency_PG13 = []
for i in RIO_PG13[:-12]:
    currency_PG13.append("${:,.2f}".format(i))
print(currency_PG13) #showing the currency_PG13 list

['$287.60', '$186.80', '$165.90', '$139.10', '$110.20', '$94.10', '$80.90', '$76.00', '$75.20', '$74.60', '$73.40', '$62.10', '$61.20', '$55.90', '$53.10', '$51.60', '$48.80', '$46.80', '$46.40', '$42.80', '$40.20', '$36.90', '$33.20', '$32.70', '$32.40', '$32.10', '$30.60', '$30.00', '$29.70', '$29.40', '$28.70', '$27.90', '$27.90', '$25.90', '$25.30', '$23.60', '$23.20', '$22.80', '$21.60', '$20.70', '$17.40', '$17.30', '$16.80', '$16.60', '$16.30', '$15.40', '$14.40', '$14.30', '$13.70', '$13.00', '$12.90', '$12.40', '$11.70', '$9.60', '$8.80', '$7.60', '$6.50', '$5.80', '$4.50', '$3.70', '$2.40', '$1.90', '$1.10', '$1.00']


len(currency_PG13)

64


final_name_pg13 = []
reversed_name = []
for x,i in enumerate(pg13_name):
    reversed_name.append((pg13_percent_profit[x], i))
reversed_name.sort(reverse = True)
for i in reversed_name[:-12]:
    final_name_pg13.append(i[1])
print(final_name_pg13) #showing the final_name_pg13 list

['Lights Out', 'A Quiet Place', 'Courageous', 'Like Crazy', 'Another Earth', 'Me Before You', 'Ouija: Origin of Evil', 'The Woman in Black', 'The Help', 'Sing', 'Still Alice', 'True Grit', 'If I Stay', 'The Vow', 'Gravity', 'Everything, Everything', 'Ida', 'Dear John', 'Brooklyn', 'Gifted', 'Step Up Revolution', 'Creed', 'Arrival', 'Creed II', 'The Impossible', 'The Bye Bye Man', 'Bridge of Spies', 'The Book Thief', 'Mustang', 'One Day', 'The Lucky One', 'Before I Fall', 'Amour', 'The Post', 'Remember Me', 'Safe Haven', 'Rings', 'The Roommate', 'Mud', 'Water for Elephants', 'Project Almanac', 'The Words', 'Fences', 'The Giver', 'The Rite', 'The Perks of Being a Wallflower', 'Black or White', 'Suffragette', 'Collateral Beauty', 'The Age of Adaline', 'Contagion', 'Beastly', 'Hereafter', 'Wish Upon', 'The Longest Ride', 'The Tree of Life', 'Burlesque', 'The Best of Me', 'Anna Karenina', 'Country Strong', 'Rabbit Hole', 'Draft Day', 'The Light Between Oceans', 'Charlie St. Cloud']


len(final_name_pg13)

64


avg_PG13 = statistics.mean(RIO_PG13[:-12])
avg_PG13

41.44375


np.percentile(RIO_PG13[:-12], [25,50,75])

array([14.15, 27.9 , 49.5 ])


dataframe_RIO_pg13 = pd.DataFrame({"Name of Movie":final_name_pg13, 
                                   "Money Generated for Every $1 Spent":currency_PG13})


dataframe_RIO_pg13


RIO_NC = []
for i in nc17_percent_profit:
    i /= 10
    RIO_NC.append(i)
    
RIO_NC.sort(reverse=True)
print(RIO_NC) #showing the RIO_NC list

[334.8, 279.2, 191.7, 167.6, 159.3, 155.7, 145.7, 128.9, 126.1, 126.1, 99.3, 80.0, 66.1, 38.7, 37.8, 34.7, 33.4, 33.4, 28.2, 21.4, 21.4, 21.4, 21.4, 16.1, 14.0, 13.2, 10.4, 6.9, 4.8, 3.9, 0.7, 0.2, 0.1, 0.1, -0.7, -1.6, -5.2, -5.3, -5.5, -5.5, -6.0, -6.3, -6.9, -7.8, -7.9, -8.5, -8.7, -9.0, -9.3]


len(RIO_NC[:-15])

34


currency_NC = []
for i in RIO_NC[:-15]:
    currency_NC.append("${:,.2f}".format(i))
print(currency_NC) #showing the currency_NC list

['$334.80', '$279.20', '$191.70', '$167.60', '$159.30', '$155.70', '$145.70', '$128.90', '$126.10', '$126.10', '$99.30', '$80.00', '$66.10', '$38.70', '$37.80', '$34.70', '$33.40', '$33.40', '$28.20', '$21.40', '$21.40', '$21.40', '$21.40', '$16.10', '$14.00', '$13.20', '$10.40', '$6.90', '$4.80', '$3.90', '$0.70', '$0.20', '$0.10', '$0.10']


len(currency_NC)

34


final_name_NC = []
reversed_name = []
for x,i in enumerate(nc17_name):
    reversed_name.append((nc17_percent_profit[x], i))
reversed_name.sort(reverse = True)
for i in reversed_name[:-15]:
    final_name_NC.append(i[1])
print(final_name_NC) #showing the final_name_NC list

['Pink Flamingos', 'Last Tango in Paris', 'Whore 1991', 'Hell', 'Clerks', 'Blue Valentine', 'Crash', 'Tokyo Decadence', 'Kids', 'Kids', 'Crash', 'Beyond the Valley of the Dolls', 'The Evil Dead', 'Blue Is the Warmest Colour', 'Blue Is the Warmest Colour', 'Lust, Caution', 'Se, jie', 'Lust, Caution ', 'Arabian Nights', 'Shame', 'Shame', 'Shame', 'Shame', 'Happiness 1998', 'Law of Desire', 'Two Girls and a Guy', 'Bad Lieutenant', 'Wide Sargasso Sea', 'Natural Born Killers', 'Matador', 'Elles', 'The Dreamers', 'Whore', 'The Dreamers']


len(final_name_NC)

34


avg_NC = statistics.mean(RIO_NC[:-15])
avg_NC

71.25588235294117


np.percentile(RIO_NC[:-15], [25,50,75])

array([ 13.4,  33.4, 126.1])


dataframe_RIO_NC = pd.DataFrame({"Name of Movie":final_name_NC, 
                                 "Money Generated for Every $1 Spent":currency_NC})


dataframe_RIO_NC


dataframe_RIO_r1  = dataframe_RIO_r[:19].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #ff5500')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#ff5500")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #ff5500'),
                                                                           ("color","#ff5500")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#ff5500')]}])


dfi.export(dataframe_RIO_r1, 'dataframe_RIO_r1.png')


dataframe_RIO_r2  = dataframe_RIO_r[19:37].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #ff5500')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#ff5500")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #ff5500'),
                                                                           ("color","#ff5500")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#ff5500')]}])


dfi.export(dataframe_RIO_r2, 'dataframe_RIO_r2.png')


dataframe_RIO_r3  = dataframe_RIO_r[37:].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #ff5500')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#ff5500")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #ff5500'),
                                                                           ("color","#ff5500")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#ff5500')]}])


dfi.export(dataframe_RIO_r3, 'dataframe_RIO_r3.png')


dataframe_RIO_g1 = dataframe_RIO_g[:12].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid red')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","red")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid red'),
                                                                           ("color","red")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','red')]}])


dfi.export(dataframe_RIO_g1, 'dataframe_RIO_g1.png')


dataframe_RIO_g2 = dataframe_RIO_g[12:].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid red')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","red")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid red'),
                                                                           ("color","red")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','red')]}])


dfi.export(dataframe_RIO_g2, 'dataframe_RIO_g2.png')


dataframe_RIO_pg1 = dataframe_RIO_pg[:22].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #fa5f55')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#fa5f55")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #fa5f55'),
                                                                           ("color","#fa5f55")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#fa5f55')]}])


dfi.export(dataframe_RIO_pg1, 'dataframe_RIO_pg1.png')


dataframe_RIO_pg2 = dataframe_RIO_pg[22:].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #fa5f55')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#fa5f55")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #fa5f55'),
                                                                           ("color","#fa5f55")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#fa5f55')]}])


dfi.export(dataframe_RIO_pg2, 'dataframe_RIO_pg2.png')


dataframe_RIO_pg131 = dataframe_RIO_pg13[:22].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #DE3163')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#DE3163")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #DE3163'),
                                                                           ("color","#DE3163")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#DE3163')]}])


dfi.export(dataframe_RIO_pg131, 'dataframe_RIO_pg131.png')


dataframe_RIO_pg132 = dataframe_RIO_pg13[22:42].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #DE3163')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#DE3163")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #DE3163'),
                                                                           ("color","#DE3163")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#DE3163')]}])


dfi.export(dataframe_RIO_pg132, 'dataframe_RIO_pg132.png')


dataframe_RIO_pg133 = dataframe_RIO_pg13[42:].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #DE3163')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#DE3163")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #DE3163'),
                                                                           ("color","#DE3163")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#DE3163')]}])


dfi.export(dataframe_RIO_pg133, 'dataframe_RIO_pg133.png')


dataframe_RIO_NC1 = dataframe_RIO_NC[:17].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #581845')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#581845")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #581845'),
                                                                           ("color","#581845")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#581845')]}])


dfi.export(dataframe_RIO_NC1, 'dataframe_RIO_NC1.png')


dataframe_RIO_NC2 = dataframe_RIO_NC[17:].style.set_table_styles([{'selector':' ', 'props': [('border','10px solid #581845')]},
                                     {"selector":"thead", 'props':[("background-color","white"), 
                                    ("color","#581845")]},
                            {'selector':"td", "props":[("background-color","white"),('border-bottom',
                                                                                    '4px solid #581845'),
                                                                           ("color","#581845")]},
                        {'selector':'th.row_heading', 'props':[('background-color','white'),
                                                              ('color','#581845')]}])


dfi.export(dataframe_RIO_NC2, 'dataframe_RIO_NC2.png')


cost = []
for i in system_rating_r.Cost:
    i = int(i.replace('$', '').replace(',', ''))
    cost.append(i)
print(cost) #showing the cost list

[100000000, 61000000, 60000000, 55000000, 55000000, 55000000, 52500000, 40000000, 37500000, 31000000, 23000000, 22500000, 22500000, 21000000, 20000000, 20000000, 13000000, 13000000, 13000000, 12000000, 12000000, 11800000, 11000000, 10000000, 9400000, 8500000, 7000000, 5000000, 4900000, 4750000, 4000000, 3500000, 3400000, 3300000, 3000000, 2000000, 2000000, 2000000, 2000000, 2000000, 2000000, 1987650, 1500000, 1000000, 1000000, 1000000, 135000, 100000, 6000000, 8500000, 20000000, 100000, 2700000, 11500000, 9000000]


len(cost)

55


df_cost_r = pd.DataFrame({"Cost":cost})


df_cost_r


x = statistics.mean(cost)
print("Arithmetic Mean of the cost for the R-rated movies is:", x)

Arithmetic Mean of the cost for the R-rated movies is: 16455866.363636363


print("Median of the cost for the R-rated movies is:", statistics.median(cost))

Median of the cost for the R-rated movies is: 9000000


print("Mode of the cost for the R-rated movies is:",statistics.mode(cost))

Mode of the cost for the R-rated movies is: 2000000


print("Standard deviation of the cost for the R-rated movies is:", np.std(cost, ddof=1))

Standard deviation of the cost for the R-rated movies is: 20757148.21084636


print("Variance of the cost for the R-rated movies is:",statistics.variance(cost))

Variance of the cost for the R-rated movies is: 430859201847042.1


cv = lambda x: np.std(x, ddof=1) / np.mean(x) * 100
print("Coefficient of Variation of the cost for the R-rated movies is:", cv(cost))

Coefficient of Variation of the cost for the R-rated movies is: 126.13828863313347


# First quartile (Q1)
Q1 = np.percentile(cost, 25, interpolation = 'midpoint')
print("The Q1 of the cost for the R-rated movies is:",Q1)

The Q1 of the cost for the R-rated movies is: 2350000.0


# Third quartile (Q3)
Q3 = np.percentile(cost, 75, interpolation = 'midpoint')
print("The Q3 of the cost for the R-rated movies is:",Q3)

The Q3 of the cost for the R-rated movies is: 20500000.0


# Interquaritle range (IQR)
IQR = Q3 - Q1
print("The interquaritle range of the cost for the R-rated movies is:",IQR)

The interquaritle range of the cost for the R-rated movies is: 18150000.0


def pearsons(mean, median, standard_deviation):
    skewness = (mean-median)*3/standard_deviation
    return skewness
print("Pearson’s Coefficient of Skewness of the cost for the R-rated movies is:", 
      pearsons( statistics.mean(cost),statistics.median(cost),np.std(cost, ddof=1)))

Pearson’s Coefficient of Skewness of the cost for the R-rated movies is: 1.0775853630616372


def chebyshevs(mean, standard_deviation, num_std, previous_p):
    position_std = num_std*standard_deviation
    upper_range = mean - position_std 
    if upper_range < 0: upper_range = 0
    lower_range = position_std + mean
    if num_std == 2: 
        print('At least 75% of the butget of the r-rated movies ranges from',upper_range,'to',lower_range)
    if num_std == 3: 
        print('At least 13.9% of the butget of the r-rated movies ranges from',previous_p,'to',lower_range)
chebyshevs(16455866, 20757148, 2, 0)
chebyshevs(16455866, 20757148, 3, 57970162)

At least 75% of the butget of the r-rated movies ranges from 0 to 57970162
At least 13.9% of the butget of the r-rated movies ranges from 57970162 to 78727310


print('Kurtosis of the budget of the r-rated movies is:',kurtosis(cost, fisher=False))
print('Excess Kurtosis of the budget of the r-rated movies is:',
      (kurtosis(cost,fisher=False)-3))#leptokurtic

Kurtosis of the budget of the r-rated movies is: 6.718303925498721
Excess Kurtosis of the budget of the r-rated movies is: 3.718303925498721


print("Arithmetic Mean of the cost for the R-rated movies is:", statistics.mean(cost))
print('10% Trimmed mean of the budget of the r-rated movies is:',stats.trim_mean(cost, 0.10))

Arithmetic Mean of the cost for the R-rated movies is: 16455866.363636363
10% Trimmed mean of the budget of the r-rated movies is: 12705281.111111112


stats.zscore(cost)

array([ 4.06193284,  2.16574487,  2.11712467,  1.87402365,  1.87402365,
        1.87402365,  1.75247314,  1.14472059,  1.02317007,  0.70713875,
        0.31817711,  0.29386701,  0.29386701,  0.22093671,  0.1723165 ,
        0.1723165 , -0.16802493, -0.16802493, -0.16802493, -0.21664513,
       -0.21664513, -0.22636917, -0.26526534, -0.31388554, -0.34305766,
       -0.38681585, -0.45974615, -0.55698656, -0.56184858, -0.56914161,
       -0.60560677, -0.62991687, -0.63477889, -0.63964091, -0.65422697,
       -0.70284717, -0.70284717, -0.70284717, -0.70284717, -0.70284717,
       -0.70284717, -0.70344763, -0.72715728, -0.75146738, -0.75146738,
       -0.75146738, -0.79352386, -0.79522556, -0.50836636, -0.38681585,
        0.1723165 , -0.79522556, -0.66881303, -0.24095523, -0.36250575])


micro_bud = 0
low_bud = 0
mid_bud = 0
high_bud = 0
for i in cost:
    if 0 <= i <= 100000:micro_bud+=1
for i in cost:
    if 100001 <= i <= 15000000:low_bud+=1
for i in cost:
    if 15000001 <= i <= 50000000:mid_bud+=1
for i in cost:
    if 50000001 <= i:high_bud+=1


micro_bud,low_bud,mid_bud,high_bud

(2, 36, 10, 7)


def Bernoulli_Dist(micro,low,mid,high,n):
    micro_p = micro / n
    low_p = low / n
    mid_p = mid / n 
    high_p = high / n
    return micro_p, low_p, mid_p, high_p


p_vals = Bernoulli_Dist(micro_bud,low_bud,mid_bud,high_bud,55)
p_vals

(0.03636363636363636,
 0.6545454545454545,
 0.18181818181818182,
 0.12727272727272726)


group1 = 0
group2 =0 
group3 = 0
for i in cost:
    if 1000000 <= i <= 5000000:group1+=1
for i in cost:
    if 5000001 <= i <= 10000000:group2+=1
for i in cost:
    if 10000001 <= i <=15000000:group3+=1


group1,group2,group3

(20, 7, 8)


p_vals1 = Bernoulli_Dist(group1,group2,group3,0,35)
p_vals1

(0.5714285714285714, 0.2, 0.22857142857142856, 0.0)


group1 = 0
group2 =0 
group3 = 0
for i in cost:
    if 15000001 <= i <= 20000000:group1+=1
for i in cost:
    if 20000001 <= i <= 30000000:group2+=1
for i in cost:
    if 30000001 <= i <=50000000:group3+=1


group1,group2,group3

(3, 4, 3)


p_vals2 = Bernoulli_Dist(group1,group2,group3,0,10)
p_vals2

(0.3, 0.4, 0.3, 0.0)


group1 = 0
group2 =0 
group3 = 0
for i in cost:
    if 50000001 <= i <= 60000000:group1+=1
for i in cost:
    if 60000001 <= i <= 70000000:group2+=1
for i in cost:
    if 90000000 <= i <=100000000:group3+=1


group1,group2,group3

(5, 1, 1)


p_vals3 = Bernoulli_Dist(group1,group2,group3,0,7)
p_vals3

(0.7142857142857143, 0.14285714285714285, 0.14285714285714285, 0.0)


freq_demo = []
for i in cost:
    freq_demo.append((round(i, -6)))
print(freq_demo) #showing the freq_demo list

[100000000, 61000000, 60000000, 55000000, 55000000, 55000000, 52000000, 40000000, 38000000, 31000000, 23000000, 22000000, 22000000, 21000000, 20000000, 20000000, 13000000, 13000000, 13000000, 12000000, 12000000, 12000000, 11000000, 10000000, 9000000, 8000000, 7000000, 5000000, 5000000, 5000000, 4000000, 4000000, 3000000, 3000000, 3000000, 2000000, 2000000, 2000000, 2000000, 2000000, 2000000, 2000000, 2000000, 1000000, 1000000, 1000000, 0, 0, 6000000, 8000000, 20000000, 0, 3000000, 12000000, 9000000]


len(freq_demo)

55


index_freq = []
for i,x in enumerate(freq_demo):index_freq.append((i,x))
print(index_freq) #showing the index_freq list

[(0, 100000000), (1, 61000000), (2, 60000000), (3, 55000000), (4, 55000000), (5, 55000000), (6, 52000000), (7, 40000000), (8, 38000000), (9, 31000000), (10, 23000000), (11, 22000000), (12, 22000000), (13, 21000000), (14, 20000000), (15, 20000000), (16, 13000000), (17, 13000000), (18, 13000000), (19, 12000000), (20, 12000000), (21, 12000000), (22, 11000000), (23, 10000000), (24, 9000000), (25, 8000000), (26, 7000000), (27, 5000000), (28, 5000000), (29, 5000000), (30, 4000000), (31, 4000000), (32, 3000000), (33, 3000000), (34, 3000000), (35, 2000000), (36, 2000000), (37, 2000000), (38, 2000000), (39, 2000000), (40, 2000000), (41, 2000000), (42, 2000000), (43, 1000000), (44, 1000000), (45, 1000000), (46, 0), (47, 0), (48, 6000000), (49, 8000000), (50, 20000000), (51, 0), (52, 3000000), (53, 12000000), (54, 9000000)]


len(index_freq)

55


freq_demo[48] = 10000000
freq_demo[6] = 55000000
freq_demo[22] = 10000000
freq_demo[49] = 10000000
freq_demo[8] = 40000000
freq_demo[10] = 20000000
freq_demo[11] = 20000000
freq_demo[12] = 20000000
freq_demo[13] = 20000000
freq_demo[24] = 10000000
freq_demo[25] = 10000000
freq_demo[26] = 10000000
freq_demo[54] = 10000000
freq_demo[1] = 60000000
freq_demo[2] = 60000000
freq_demo[-4] = 100000
freq_demo[-8] = 100000
freq_demo[-9] = 100000


freq_demo1 = Counter((freq_demo))
print(freq_demo1)#showing the freq_demo1 dicttionary

Counter({10000000: 8, 2000000: 8, 20000000: 7, 55000000: 4, 12000000: 4, 3000000: 4, 13000000: 3, 5000000: 3, 1000000: 3, 100000: 3, 60000000: 2, 40000000: 2, 4000000: 2, 100000000: 1, 31000000: 1})


freq_one = sorted(freq_demo1.items(), key=lambda i: i[0])
print(freq_one)#showing the freq_one list

[(100000, 3), (1000000, 3), (2000000, 8), (3000000, 4), (4000000, 2), (5000000, 3), (10000000, 8), (12000000, 4), (13000000, 3), (20000000, 7), (31000000, 1), (40000000, 2), (55000000, 4), (60000000, 2), (100000000, 1)]


cost_freq = []
cost_freq_amount = []
for i in freq_one: 
    cost_freq_amount.append(i[1])
    cost_freq.append("${:,.0f}".format(i[0]))


print(cost_freq)#showing the cost_freq list

['$100,000', '$1,000,000', '$2,000,000', '$3,000,000', '$4,000,000', '$5,000,000', '$10,000,000', '$12,000,000', '$13,000,000', '$20,000,000', '$31,000,000', '$40,000,000', '$55,000,000', '$60,000,000', '$100,000,000']


len(cost_freq)

15


print(cost_freq_amount)#showing the cost_freq_amount list

[3, 3, 8, 4, 2, 3, 8, 4, 3, 7, 1, 2, 4, 2, 1]


len(cost_freq_amount)

15


freq_dis = pd.DataFrame({"Amount of Budget (x)":cost_freq,
                                 "Frequency (f)":cost_freq_amount})


freq_dis


def chunks(lst, n):
    """Yield successive n-sized chunks from lst."""
    for i in range(0, len(lst), n):
        yield lst[i:i + n]
        
a =list(chunks(range(90001, 100000000), 10000000))
a

[range(90001, 10090001),
 range(10090001, 20090001),
 range(20090001, 30090001),
 range(30090001, 40090001),
 range(40090001, 50090001),
 range(50090001, 60090001),
 range(60090001, 70090001),
 range(70090001, 80090001),
 range(80090001, 90090001),
 range(90090001, 100000000)]


lower_val = ['$90,000','$10,080,001', '$20,080,002', '$30,080,003', '$40,080,004', 
             '$50,080,005', '$60,080,006', '$70,080,007', '$80,080,008', '$90,080,009' ]
print(lower_val)#showing the lower_val list

['$90,000', '$10,080,001', '$20,080,002', '$30,080,003', '$40,080,004', '$50,080,005', '$60,080,006', '$70,080,007', '$80,080,008', '$90,080,009']


len(lower_val)

10


upper_val = ['$10,080,000','$20,080,001','$30,080,002','$40,080,003','$50,080,004',
  '$60,080,005','$70,080,006','$80,080,007','$90,080,008', '$100,080,009']
print(upper_val)#showing the upper_val list

['$10,080,000', '$20,080,001', '$30,080,002', '$40,080,003', '$50,080,004', '$60,080,005', '$70,080,006', '$80,080,007', '$90,080,008', '$100,080,009']


len(upper_val)

10


count1 = 0
count2 = 0
count3 = 0
count4 = 0
count5 = 0
count6 = 0
count7 = 0
count8 = 0
count9 = 0
count10 = 0
for i in cost: 
    if 90000 <= i <= 10080000:
        count1+=1
    if 10080001 <= i <= 20080001:
        count2+=1
    if 20080002 <= i <= 30080002:
        count3+=1
    if 30080003 <= i <= 40080003:
        count4+=1
    if 40080004 <= i <= 50080004:
        count5+=1
    if 50080005 <= i <= 60080005:
        count6+=1
    if 60080006 <= i <= 70080006:
        count7+=1
    if 70080007 <= i <= 80080007:
        count8+=1
    if 80080008 <= i <= 90080008:
        count9+=1
    if 90080009 <= i <= 100080009:
        count10+=1

freq_amount = [count1,count2,count3,count4,count5,count6,count7,count8,count9,count10]
print(freq_amount)#showing the freq_amount list

[30, 11, 4, 3, 0, 5, 1, 0, 0, 1]


len(freq_amount)

10


freq_amount_percent_demo = [count1/55*100,count2/55*100,count3/55*100,count4/55*100,
                       count5/55*100,count6/55*100,count7/55*100,count8/55*100,
                       count9/55*100,count10/55*100]
freq_amount_percent_demo1 = [55,20,7,5,0,9,2,0,0,2]
print(freq_amount_percent_demo1)#showing the freq_amount_percent_demo1 list

[55, 20, 7, 5, 0, 9, 2, 0, 0, 2]


len(freq_amount_percent_demo1)

10


freq_amount_percent = []
for i in freq_amount_percent_demo1:
    freq_amount_percent.append("{:}%".format(i))
print(freq_amount_percent)#showing the freq_amount_percent list

['55%', '20%', '7%', '5%', '0%', '9%', '2%', '0%', '0%', '2%']


len(freq_amount_percent)

10


def Cumulative(lists):
    cu_list = []
    length = len(lists)
    cu_list = [sum(lists[0:x:1]) for x in range(0, length+1)]
    return cu_list[1:]


freq_cumulative_amount = Cumulative(freq_amount)
print(freq_cumulative_amount)#showing the freq_cumulative_amount list

[30, 41, 45, 48, 48, 53, 54, 54, 54, 55]


len(freq_cumulative_amount)

10


freq_cumulative_percent_demo = Cumulative(freq_amount_percent_demo1)
print(freq_cumulative_percent_demo)#showing the freq_cumulative_percent_demo list

[55, 75, 82, 87, 87, 96, 98, 98, 98, 100]


len(freq_cumulative_percent_demo)

10


freq_cumulative_percent = []
for i in freq_cumulative_percent_demo:
    freq_cumulative_percent.append("{:}%".format(i))
print(freq_cumulative_percent)#showing the freq_cumulative_percent list

['55%', '75%', '82%', '87%', '87%', '96%', '98%', '98%', '98%', '100%']


len(freq_cumulative_percent)

10


freq_cum_dis = pd.DataFrame({"Lower\nValue":lower_val,
                             "Upper\nValue":upper_val,
                             "Frequency (f)":freq_amount,
                             "Percentage (%)":freq_amount_percent,
                            "Cumulative\nFrequency":freq_cumulative_amount,
                            "Cumulative\nPercentage":freq_cumulative_percent})


freq_cum_dis


count1 = 0
count2 = 0
count3 = 0
count4 = 0
count5 = 0
count6 = 0
count7 = 0
count8 = 0
count9 = 0
count10 = 0
for i in cost: 
    if i < 10000000:
        count1+=1
    if 10000000 <= i < 20000000:
        count2+=1
    if 20000000 <= i < 30000000:
        count3+=1
    if 30000000 <= i < 40000000:
        count4+=1
    if 40000000 <= i < 50000000:
        count5+=1
    if 50000000 <= i < 60000000:
        count6+=1
    if 60000000 <= i < 70000000:
        count7+=1
    if 70000000 <= i < 80000000:
        count8+=1
    if 80000000 <= i < 90000000:
        count9+=1
    if 90000000 <= i <= 100000000:
        count10+=1
freq_amount = [count1,count2,count3,count4,count5,count6,count7,count8,count9,count10]
print(freq_amount)#showing the freq_amount list

[29, 9, 7, 2, 1, 4, 2, 0, 0, 1]


len(freq_amount)

10


cum_rel_freq_demo = []
for i in freq_amount:cum_rel_freq_demo.append(i/55*100)
cum_rel_freq_demo1 = [53,16,13,3,2,7,4,0,0,2]
print(cum_rel_freq_demo1)#showing the cum_rel_freq_demo1 list

[53, 16, 13, 3, 2, 7, 4, 0, 0, 2]


len(cum_rel_freq_demo1)

10


cum_rel_freq_demo2 = Cumulative(cum_rel_freq_demo1)
print(cum_rel_freq_demo2)#showing the cum_rel_freq_demo2 list

[53, 69, 82, 85, 87, 94, 98, 98, 98, 100]


len(cum_rel_freq_demo2)

10


cum_rel_freq_percent = []
for i in cum_rel_freq_demo2:
    cum_rel_freq_percent.append("{:}%".format(i))
print(cum_rel_freq_percent)#showing the cum_rel_freq_percent list

['53%', '69%', '82%', '85%', '87%', '94%', '98%', '98%', '98%', '100%']


len(cum_rel_freq_percent)

10


freq_cumulative_amount = Cumulative(freq_amount)
print(freq_cumulative_amount)#showing the freq_cumulative_amount list

[29, 38, 45, 47, 48, 52, 54, 54, 54, 55]


len(freq_cumulative_amount)

10


intervals_cum = [ '< $10 Million','10 to < $20 Million','20 to < $30 Million',
                 '30 to < $40 Million',
 '40 to < $50 Miilion', '50 to < $60 Miilion', '60 to < $70 Miilion',
                 '70 to < $80 Miilion',
 '80 to < $90 Miilion','>= $100 Miilion']
print(intervals_cum)#showing the intervals_cum list

['< $10 Million', '10 to < $20 Million', '20 to < $30 Million', '30 to < $40 Million', '40 to < $50 Miilion', '50 to < $60 Miilion', '60 to < $70 Miilion', '70 to < $80 Miilion', '80 to < $90 Miilion', '>= $100 Miilion']


len(intervals_cum)

10


cum_rel_freq = pd.DataFrame({"Amount of Budget":intervals_cum,
                             "Frequency (f)":freq_amount,
                             "Cumulative Frequency":freq_cumulative_amount,
                             "Cumelative Relative Frequency Percentage":cum_rel_freq_percent,
                            })


cum_rel_freq


means = '16,455,866'
std = '20,757,148'

def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():
    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-70, 70)
    s = [21]
    m = [16]
    c = ['#ff5500']


    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")

   
    plt.xlim(-70, 70)
    plt.ylim(0, .2)
    plt.legend(fontsize=11)
    plt.title('Variability of Cost of R-rated Movies, Normal\n Distribution, Mean =16.4 million, StDev=21 million',fontsize=14)
    plt.xlabel("Cost of R-rated Movies",fontsize=14)
    plt.ylabel("Density",fontsize=14)
    plt.grid(False)
    plt.savefig('variability_cost_r',bbox_inches='tight',facecolor='white', transparent=False)
    plt.show()
   
    
if __name__ == '__main__':
   main()


#plt.ylim(-1,2.1) # Setting y limits so the axis are consistent
#plt.figure(figsize=(8,5))
import matplotlib.patches as mpatches
plt.ylabel('Cost of R-rated Movies',fontsize=14)
plt.xlabel('Ranking of Values',fontsize=14)
plt.title("The Variance of all the Budegt\n of all the R-rated movies in the Drama genre",fontsize=14) # Setting the title 
plt.scatter(x=df_cost_r.index, y=df_cost_r['Cost'], s=15, color='#ff5500'); # Plotting the scatter
plt.hlines(y=df_cost_r['Cost'].mean(), xmin=0, xmax=55, color='blue') # Mean line
plt.grid(False)
plt.annotate('CL - center line (Arithmetic Mean)',
            xy=(176, 102),
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('Data pionts',
            xy=(105, 180),
            color ='black',
            fontsize=11,
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',)

plt.savefig('variance_cost_r',bbox_inches='tight',facecolor='white', transparent=False)
plt.show()# Telling matplotlib to show the chart


#plt.ylim(-1,2.1) # Setting y limits so the axis are consistent
#plt.figure(figsize=(8,5))
plt.ylabel('Cost of R-rated Movies',fontsize=14)
plt.xlabel('Position of Values',fontsize=14)
plt.title("The Variance of all the Budegt\n of all the R-rated movies in the Drama genre",fontsize=14) # Setting the title 
plt.scatter(x=df_cost_r.index, y=df_cost_r['Cost'], s=15, color='#ff5500'); # Plotting the scatter
plt.hlines(y=df_cost_r['Cost'].mean(), xmin=0, xmax=55, color='blue') # Mean line

for std_int in [-3, -2, -1, 1, 2, 3]: # Going through different stds from the mean
    standard_deviation = df_cost_r['Cost'].mean() + df_cost_r['Cost'].std()*std_int
    if std_int in [1,2,-1,-2]:
        plt.hlines(y=standard_deviation,
               xmin=0,
               xmax=55,
               linestyles='dashed',
               colors='green'); # 1 std above
    
    if std_int ==-3:
        plt.hlines(y=standard_deviation,
               xmin=0,
               xmax=55,
               colors='red',); # 1 std above
    if std_int == +3:
        plt.hlines(y=standard_deviation,
               xmin=0,
               xmax=55,
               colors='red'); # 1 std above
   
    # Giving labels to the lines we just drew
    #plt.text(y=standard_deviation + 2, x=-10, s=std_int, ha='center')
    plt.grid(False)
    

plt.annotate('UCL - upper control limit',
            xy=(84, 238),
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('LCL - lower control limit',
            xy=(84, 70),
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('+3 SD',
            xy=(355, 240),
            color ='purple',
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('+2 SD',
            xy=(355, 210),
            color ='purple',
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('+1 SD',
            xy=(355, 180),
            color ='purple',
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('CL - center line (Arithmetic Mean)',
            xy=(176, 152),
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('-3 SD',
            xy=(355, 70),
            color ='purple',
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('-2 SD',
            xy=(355, 98),
            color ='purple',
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.annotate('-1 SD',
            xy=(355, 125),
            color ='purple',
            xycoords='figure pixels',
            horizontalalignment='left',
            verticalalignment='top',
            fontsize=11,)
plt.savefig('variance_std_cost_r',bbox_inches='tight',facecolor='white', transparent=False)


import matplotlib.pyplot as plt
# An "interface" to matplotlib.axes.Axes.hist() method
n, bins, patches = plt.hist(x=cost, bins='auto', color='#ff5500',
                            alpha=0.7, rwidth=0.85)
plt.grid(False)
plt.grid(axis='y', alpha=0.75)
plt.xlabel('Cost of R-rated Movies',fontsize=14)
plt.ylabel('Frequency',fontsize=14)
plt.title('The Pearson’s Coefficient of Skewness for the Budget\n of all R-rated movies is 1.07 (n=55)',fontsize=14)
plt.savefig('skew_cost_r.png', bbox_inches='tight',facecolor='white', transparent=False)


# An "interface" to matplotlib.axes.Axes.hist() method
median_cost = statistics.median(cost)
mean_cost = 16455866
mode_cost = statistics.mode(cost)
n, bins, patches = plt.hist(x=cost, bins='auto', color='#ff5500',
                            alpha=0.2, rwidth=0.85)
plt.grid(axis='y', alpha=0.75)
names = ["median", "mean", "mode"]
colors = ['green', 'red', 'blue']
measurements = [median_cost, mean_cost, mode_cost]
for measurement, name, color in zip(measurements, names, colors):
    plt.axvline(x=measurement,  linestyle='--', linewidth=2.5, label='{0} at {1}'.format(name, measurement), c=color)
plt.legend(fontsize=10);

plt.xlabel('Cost of R-rated Movies',fontsize=14)
plt.ylabel('Frequency',fontsize=14)
plt.title('Comparison of Mode, Median and Mean in the\n Distribution of the Cost of all the R-rated Drama movies',fontsize=14)
plt.savefig('skewness2_cost_r', bbox_inches='tight')


means = '16,455,866'
std = '20,757,148'
means1 = 16
std1 = 20
def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():

    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-90, 90)
    s = [21]
    m = [16]
    c = ['#ff5500']

    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")
    
    x = np.linspace(means1 - std1*2, means1 + std1*2)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x, y, alpha=0.5, color='#ff5500')
    ax.annotate('at least 75%\n at least 41 obs', xy=(50,0.0075), xytext=(50,0.0125),
            arrowprops={'arrowstyle': '-|>'}, va='center', color='black',fontsize=11)
    
   
    plt.xlim(-100, 100)
    plt.ylim(0, .02)
    plt.legend(fontsize=10)
    plt.title('Chebyshevs Theorem on the Budget \nof the R-rated Movies in the Drama Genre (n=55)',fontsize=14)
    plt.xlabel("Cost of R-rated Movies",fontsize=14)
    plt.ylabel("Density", fontsize=14)
    plt.savefig('cheb_cost_r',bbox_inches='tight')
    plt.show()

if __name__ == '__main__':
   main()


means = '16,455,866'
std = '20,757,148'
means1 = 16
std1 = 20
def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():
    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-90, 90)
    s = [21]
    m = [16]
    c = ['#ff5500']

    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")
    
    x = np.linspace(57, 78)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x, y, alpha=0.5, color='#ff5500')
    
    x1 = np.linspace(-26, -40)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x1, y, alpha=0.5, color='#ff5500')

    ax.annotate('at least 13.9%\n at leat 8 obs', xy=(70,0.0025), xytext=(50,0.0075),
            arrowprops={'arrowstyle': '-|>'}, va='center', color='black',fontsize=11)
   
    plt.xlim(-100, 100)
    plt.ylim(0, .0199)
    plt.legend(fontsize=10)
    plt.title('Chebyshevs Theorem on the Budget \nof the R-rated Movies in the Drama Genre (n=55)',fontsize=14)
    plt.xlabel("Cost of R-rated Movies",fontsize=14)
    plt.ylabel("Density",fontsize=14)
    plt.savefig('cheb2_cost_r',bbox_inches='tight')
    plt.show()

if __name__ == '__main__':
   main()


import seaborn as sns
sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.stripplot(data=df_cost_r, color='#ff5500');
sns.violinplot( data=df_cost_r,inner=None,color='0.8').set(title='KDE and Jittered strip plot\n on the budget of the r-rated movies')
plt.savefig('violin_cost_r')
plt.show()


sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.swarmplot(data=df_cost_r, color='#ff5500');
sns.violinplot( data=df_cost_r, color='0.8', inner=None, aplha=.2).set(title='KDE and swarm plot\n on the budget of the r-rated movies')
#sns.despine()
plt.savefig('violin2_cost_r')
plt.show()

C:\Users\rutho\AppData\Local\Temp/ipykernel_8212/229341393.py:8: UserWarning: Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.
  plt.show()


sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.stripplot(data=df_cost_r, color='#ff5500', jitter=False)
sns.violinplot(data=df_cost_r,  split=True,inner=None,
      scale="count", color='0.8', alpha=.1).set(title='KDE and rug plot\n on the budget of the r-rated movies')
#sns.despine()
plt.savefig('violin3_cost_r')
plt.show()

C:\Users\rutho\AppData\Local\Temp/ipykernel_8212/3008613242.py:9: UserWarning: Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.
  plt.show()


sns.set(font_scale=.85)
plt.gcf().set_size_inches(4.2, 4)
sns.set_style("whitegrid")
ax = sns.violinplot( data=df_cost_r,color='#ff5500',fill=True,width=0.6,scale="width", inner=None)
sns.boxplot( data=df_cost_r, color='#ff5500', width=0.3,  ax=ax).set(title='KDE and Box plot\n on the budget of the r-rated movies')
for violin, alpha in zip(ax.collections[::2], [0.3]):violin.set_alpha(alpha)
plt.savefig('violin4_cost_r')


sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.displot(df_cost_r, x="Cost",color='#ff5500', kind="kde",
           fill=True).set(title='KDE on the Budget of the R-rated Drama Movies')
plt.xlim(0, None)
plt.savefig('skewness3_cost_r')
plt.show()

C:\Users\rutho\AppData\Local\Temp/ipykernel_8212/292974908.py:8: UserWarning: Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.
  plt.show()

<Figure size 417.6x432 with 0 Axes>


import matplotlib.pyplot as plt
from scipy.stats import bernoulli
#
# Instance of Bernoulli distribution with parameter p = 0.7
#
bd = bernoulli(p_vals[0])#4%
#
# Outcome of experiment can take value as 0, 1
#
X = [0, 1]
#
# Create a bar plot; Note the usage of "pmf" function
# to determine the probability of different values of
# random variable
#
plt.figure(figsize=(7,7))
plt.rcParams['axes.facecolor'] = '#FFFAF0'
plt.xlim(-1, 2)
plt.bar(X, bd.pmf(X), color='#ff5500')
plt.title('Bernoulli Distribution (p=0.036)', fontsize='15')
plt.xlabel('Values of Random Variable X (0, 1)', fontsize='15')
plt.ylabel('Probability', fontsize='15')
plt.rcParams["axes.edgecolor"] = "black"
plt.rc('grid', linestyle="-", color='grey',alpha=0.2)
plt.grid(True)
plt.savefig('Bernoulli_dist_cost_r',bbox_inches='tight')
plt.show()


import matplotlib.pyplot as plt
from scipy.stats import bernoulli
#
# Instance of Bernoulli distribution with parameter p = 0.7
#
bd = bernoulli(p_vals[1])#65%
#
# Outcome of experiment can take value as 0, 1
#
X = [0, 1]
#
# Create a bar plot; Note the usage of "pmf" function
# to determine the probability of different values of
# random variable
#
plt.figure(figsize=(7,7))
plt.rcParams['axes.facecolor'] = '#FFFAF0'
plt.xlim(-1, 2)
plt.bar(X, bd.pmf(X), color='#ff5500')
plt.title('Bernoulli Distribution (p=0.65)', fontsize='15')
plt.xlabel('Values of Random Variable X (0, 1)', fontsize='15')
plt.ylabel('Probability', fontsize='15')
plt.rcParams["axes.edgecolor"] = "black"
plt.rc('grid', linestyle="-", color='grey',alpha=0.2)
plt.grid(True)
plt.savefig('Bernoulli1_dist_cost_r',bbox_inches='tight')
plt.show()


import matplotlib.pyplot as plt
from scipy.stats import bernoulli
#
# Instance of Bernoulli distribution with parameter p = 0.7
#
bd = bernoulli(p_vals[2])#18%
#
# Outcome of experiment can take value as 0, 1
#
X = [0, 1]
#
# Create a bar plot; Note the usage of "pmf" function
# to determine the probability of different values of
# random variable
#
plt.figure(figsize=(7,7))
plt.rcParams['axes.facecolor'] = '#FFFAF0'
plt.xlim(-1, 2)
plt.bar(X, bd.pmf(X), color='#ff5500')
plt.title('Bernoulli Distribution (p=0.18)', fontsize='15')
plt.xlabel('Values of Random Variable X (0, 1)', fontsize='15')
plt.ylabel('Probability', fontsize='15')
plt.rcParams["axes.edgecolor"] = "black"
plt.rc('grid', linestyle="-", color='grey',alpha=0.2)
plt.grid(True)
plt.savefig('Bernoulli2_dist_cost_r',bbox_inches='tight')
plt.show()


import matplotlib.pyplot as plt
from scipy.stats import bernoulli
#
# Instance of Bernoulli distribution with parameter p = 0.7
#
bd = bernoulli(p_vals[3])#13%
#
# Outcome of experiment can take value as 0, 1
#
X = [0, 1]
#
# Create a bar plot; Note the usage of "pmf" function
# to determine the probability of different values of
# random variable
#
plt.figure(figsize=(7,7))
plt.rcParams['axes.facecolor'] = '#FFFAF0'
plt.xlim(-1, 2)
plt.bar(X, bd.pmf(X), color='#ff5500')
plt.title('Bernoulli Distribution (p=0.13)', fontsize='15')
plt.xlabel('Values of Random Variable X (0, 1)', fontsize='15')
plt.ylabel('Probability', fontsize='15')
plt.rcParams["axes.edgecolor"] = "black"
plt.rc('grid', linestyle="-", color='grey',alpha=0.2)
plt.grid(True)
plt.savefig('Bernoulli3_dist_cost_r',bbox_inches='tight')
plt.show()


from scipy import stats
import matplotlib.style as style
plt.figure(figsize=(5,3))
stats.probplot(cost,plot=plt)
#ax = fig.subplots()
#ax = fig.add_subplot()
#fig, ax = plt.subplots()
#ax.get_lines()[0].set_markerfacecolor('C0')
plt.title("Distribution Plot of the Budgets of R-rated Drama Movies",fontsize=10)
plt.xlabel('Theoretical Quantiles',fontsize=10)
plt.ylabel('Ordered Values',fontsize=10)
plt.savefig('Probab_plot_r3',bbox_inches='tight',facecolor='white', transparent=False)
plt.show()


%%html
<script src="https://code.jquery.com/jquery-3.3.1.min.js" integrity="sha256-FgpCb/KJQlLNfOu91ta32o/NMZxltwRo8QtmkMRdAu8=" crossorigin="anonymous"></script>
<link href="https://cdn.webdatarocks.com/latest/webdatarocks.min.css" rel="stylesheet" />
<script src="https://cdn.webdatarocks.com/latest/webdatarocks.toolbar.min.js"></script>
<script src="https://cdn.webdatarocks.com/latest/webdatarocks.js"></script>
<script src="https://code.highcharts.com/4.2.2/highcharts.js"></script>
<script src="https://code.highcharts.com/4.2.2/highcharts-more.js"></script>
<script src="https://cdn.webdatarocks.com/latest/webdatarocks.highcharts.js"></script>
<figure class="highcharts-figure">
    <div id="containerr"></div>
</figure>


%%js
Highcharts.chart('containerr', {
    chart: {
        width:950,
        height:500,
        styledMode: false,
        plotBackgroundColor: null,
        plotBorderWidth: null,
        plotShadow: false,
        type: 'pie'
       
    },
    title: {
        text: 'The Bernoulli Distribution on the Budgets of R-rated Drama Movies'
    },
    tooltip: {
        pointFormat: '{series.name}: <b>{point.percentage:.1f}%</b>'
    },
    legend: {
        enabled: true,
        verticalAlign: 'bottom',
        symbolRadius: 20,
        reversed: true
    },
    accessibility: {
        point: {
            valueSuffix: '%'
        }
    },
    plotOptions: {
        pie: {
            allowPointSelect: true,
            cursor: 'pointer',
            dataLabels: {
                enabled: true,
                format: '<b>{point.name}</b>: {point.percentage:.1f} %'
                
            },
            showInLegend: true
        }
    },
    series: [{
        name: 'System Rating',
        colorByPoint: true,
        colors: ['#ba450b','#ff5500','#e8946a','#f0c3ad'],
        data: [{
            name:'Micro Budget: <br>$0 to $100,000',
            y: 3
        }, {
            name: 'Low Budget: <br>$100,000 to $15 Million',
            y: 35
        }, {
            name: 'Mid Budget: <br>$15 Million to $50 Million',
            y: 10,
            sliced: true,
            selected: true
        }, {
            name: 'High Budget: <br>$50 Million+',
            y: 7
        }]
    }]
});


%%html
<script src="https://code.jquery.com/jquery-3.3.1.min.js" integrity="sha256-FgpCb/KJQlLNfOu91ta32o/NMZxltwRo8QtmkMRdAu8=" crossorigin="anonymous"></script>
<link href="https://cdn.webdatarocks.com/latest/webdatarocks.min.css" rel="stylesheet" />
<script src="https://cdn.webdatarocks.com/latest/webdatarocks.toolbar.min.js"></script>
<script src="https://cdn.webdatarocks.com/latest/webdatarocks.js"></script>
<script src="https://code.highcharts.com/4.2.2/highcharts.js"></script>
<script src="https://code.highcharts.com/4.2.2/highcharts-more.js"></script>
<script src="https://cdn.webdatarocks.com/latest/webdatarocks.highcharts.js"></script>

<table><tr><th></th><th></th><th></th><th></th></tr><tr><th></th><th></th><th></th><th></th></tr></th><th></th></tr>
    <tr>
    <td><div id="container"></div><td>
    <td><div id="container1"></div><td>
    <td><div id="container2"></div><td>
    </tr>
</table>


%%js
Highcharts.chart('container', {
    chart: {
        type: 'column',
    },
    title: {
        text: 'The Bernoulli Distribution on <br>the Sub-groups in the Low-Budget Category'
    },
    subtitle: {
        text: 'R-rated Drama Movies'
    },
    xAxis: {
        type: 'category',
        labels: {
            style: {
                fontSize: '13px',
                fontFamily: 'Verdana, sans-serif'
            }
        }
    },
    yAxis: {
        min: 0,
        title: {
            text: 'Probability (%)'
        }
    },
    legend: {
        enabled: true,
        verticalAlign: 'bottom',
        symbolRadius: 20,
        reversed: true
    },
    plotOptions: {
        series: {
            borderWidth: 0,
            dataLabels: {
                enabled: true,
                format: '{point.y:.0f}%'
            }
        }
    },
    tooltip: {
        pointFormat: 'Percentage: <b>{point.y:.0f} %</b>'
    },
    series: [{
        color: '#ff5500',
        name: 'Compared to the Sub-groups within the Low-Budget category',
        data: [
            ['$1 Million to $5 Million', 57],
            ['$5 Million to $10 Million', 20],
            ['$10 Million to $15 Million', 23]
        ]
    }, {
        color: '#ba450b',
        name: 'Compared to the entire Data set',
        data: [
            ['$1 Million to $5 Million', 36],
            ['$5 Million to $10 Million', 13],
            ['$10 Million to $15 Million', 15]
        ]
    }]
});


%%js
Highcharts.chart('container1', {
    chart: {
        type: 'column',
    },
    title: {
        text: 'The Bernoulli Distribution on <br>the Sub-groups in the Mid-Budget Category'
    },
    subtitle: {
        text: 'R-rated Drama Movies'
    },
    xAxis: {
        type: 'category',
        labels: {
            style: {
                fontSize: '13px',
                fontFamily: 'Verdana, sans-serif'
            }
        }
    },
    yAxis: {
        min: 0,
        title: {
            text: 'Probability (%)'
        }
    },
    legend: {
        enabled: true,
        verticalAlign: 'bottom',
        symbolRadius: 20,
        reversed: true
    },
    plotOptions: {
        series: {
            borderWidth: 0,
            dataLabels: {
                enabled: true,
                format: '{point.y:.0f}%'
            }
        }
    },
    tooltip: {
        pointFormat: 'Percentage: <b>{point.y:.0f} %</b>'
    },
    series: [{
        color: '#e8946a',
        name: 'Compared to the Sub-groups within the Mid-Budget category',
        data: [
            ['$15 Million to $20 Million', 30],
            ['$20 Million to $30 Million', 40],
            ['$30 Million to $50 Million', 30]
        ]
    }, {
        color: '#ba450b',
        name: 'Compared to the entire Data set',
        data: [
            ['$15 Million to $20 Million', 6],
            ['$20 Million to $30 Million', 7],
            ['$30 Million to $50 Million', 6]
        ]
    }]
});


%%js
Highcharts.chart('container2', {
    chart: {
        type: 'column',
        
    },
    title: {
        text: 'The Bernoulli Distribution on <br>the Sub-groups in the High-Budget Category'
    },
    subtitle: {
        text: 'R-rated Drama Movies'
    },
    xAxis: {
        type: 'category',
        labels: {
            style: {
                fontSize: '13px',
                fontFamily: 'Verdana, sans-serif'
            }
        }
    },
    yAxis: {
        min: 0,
        title: {
            text: 'Probability (%)'
        }
    },
    legend: {
        enabled: true,
        verticalAlign: 'bottom',
        symbolRadius: 20,
        reversed: true
    },
    plotOptions: {
        series: {
            borderWidth: 0,
            dataLabels: {
                enabled: true,
                format: '{point.y:.0f}%'
            }
        }
    },
    tooltip: {
        pointFormat: 'Percentage: <b>{point.y:.0f} %</b>'
    },
    series: [{
        color: '#f0c3ad',
        name: 'Compared to the Sub-groups within the High-Budget category',
        data: [
            ['$50 Million to $60 Million', 72],
            ['$60 Million to $70 Million', 14],
            ['$90 Million to $100 Million', 14]
        ]
    }, {
        color: '#ba450b',
        name: 'Compared to the entire Data set',
        data: [
            ['$50 Million to $60 Million', 9],
            ['$60 Million to $70 Million', 2],
            ['$90 Million to $100 Million', 2]
        ]
    }]
});


freq_dis_cost_r = freq_dis[:8].style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},
                            ])


dfi.export(freq_dis_cost_r, 'freq_dis_cost_r.png')


freq1_dis_cost_r = freq_dis[8:].style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\885110614.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq1_dis_cost_r = freq_dis[8:].style.hide_index()\


dfi.export(freq1_dis_cost_r, 'freq1_dis_cost_r.png')


freq_cum_dis_cost_r = freq_cum_dis.style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black"),
                                      ("font-size", "10pt")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\4059934024.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_cum_dis_cost_r = freq_cum_dis.style.hide_index()\


dfi.export(freq_cum_dis_cost_r, 'freq_cum_dis_cost_r.png')


cum_rel_freq_cost_r = cum_rel_freq.style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black"),
                                      ("font-size", "10pt")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\348482533.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  cum_rel_freq_cost_r = cum_rel_freq.style.hide_index()\


dfi.export(cum_rel_freq_cost_r, 'cum_rel_freq_cost_r.png')


# Set up the axes and figure
fig, ax = plt.subplots()
amount = [10000000, 20000000, 30000000, 40000000, 50000000, 60000000, 70000000, 80000000, 
       90000000, 100000000]
freq = [53, 69, 82, 85, 87, 94, 98, 98, 98, 100]
x = ['$10M to < $20M','$30M to < $40M','$50M to < $60M','$70M to < $80M','>= $100M']
plt.plot( amount, freq ,color='#ff5500', marker='o')
plt.title('Cumulative relative frequency (%) of \n the amount of budget spent on R-rated movies', fontsize=14)
plt.xlabel('Amount of Budget', fontsize=14)
plt.ylabel('Cumulative relative frequency (%)', fontsize=14)
plt.grid(True)
#plt.xticks(x, rotation = 45)
plt.subplots_adjust(bottom=spacing)
plt.show()


roi = []
for i in system_rating_r['Return On Investment']:
    i = int(i.replace('$', '').replace(',', ''))
    roi.append(i)
print(roi)#showing the roi list

[349948323, 307567189, 24154026, 326398492, 316350619, 19966854, 82112435, 530998101, 13147416, 129558438, 54735925, 9898681, 8554727, 17017873, 26604054, 8270399, 318266710, 25358392, 23262783, 7859167, 23830713, 31043521, 45178935, 60133905, 12417298, 69233867, 3765283, 12499242, 12636004, 222016, 53273049, 36954520, 17033227, 35669037, 20251930, 14610760, 14131551, 9295324, 8153415, 88390, 4328516, 19282640, 12744931, 15566240, 4438911, 156309, 294448, 2669782, 48766923, 68711836, 14718173, 1851683, 556082, 1500000, 2000000]


len(roi)

55


df_roi_r = pd.DataFrame({"ROI":roi})


df_roi_r


x = statistics.mean(roi)
print("Arithmetic Mean of the ROI for the R-rated movies is:", x)

Arithmetic Mean of the ROI for the R-rated movies is: 59600710.27272727


print("Median of the ROI for the R-rated movies is:", statistics.median(roi))

Median of the ROI for the R-rated movies is: 17017873


print("Mode of the ROI for the R-rated movies is:",statistics.mode(roi))

Mode of the ROI for the R-rated movies is: 349948323


print("Standard deviation of the ROI for the R-rated movies is:", np.std(roi, ddof=1))

Standard deviation of the ROI for the R-rated movies is: 111311472.60911952


cv = lambda x: np.std(x, ddof=1) / np.mean(x) * 100
print("Coefficient of Variation of the ROI for the R-rated movies is:", cv(roi))

Coefficient of Variation of the ROI for the R-rated movies is: 186.76199008328697


def pearsons(mean, median, standard_deviation):
    skewness = (mean-median)*3/standard_deviation
    return skewness
print("Pearson’s Coefficient of Skewness of the ROI for the R-rated movies is:", 
      pearsons( statistics.mean(roi),statistics.median(roi),np.std(roi, ddof=1)))

Pearson’s Coefficient of Skewness of the ROI for the R-rated movies is: 1.147667071720293


def chebyshevs(mean, standard_deviation, num_std, previous_p):
    position_std = num_std*standard_deviation
    upper_range = mean - position_std 
    if upper_range < 0: upper_range = 0
    lower_range = position_std + mean
    if num_std == 2: 
        print('At least 75% of the ROI of the r-rated movies ranges from',upper_range,'to',lower_range)
    if num_std == 3: 
        print('At least 13.9% of the ROI of the r-rated movies ranges from',previous_p,'to',lower_range)
chebyshevs(59600710, 111311472, 2, 0)
chebyshevs(59600710, 111311472, 3, 282223654)

At least 75% of the ROI of the r-rated movies ranges from 0 to 282223654
At least 13.9% of the ROI of the r-rated movies ranges from 282223654 to 393535126


print('Kurtosis of the ROI of the r-rated movies is:',kurtosis(roi, fisher=False))
print('Excess Kurtosis of the ROI of the r-rated movies is:',
      (kurtosis(roi,fisher=False)-3))#leptokurtic

Kurtosis of the ROI of the r-rated movies is: 9.143154378370438
Excess Kurtosis of the ROI of the r-rated movies is: 6.143154378370438


print("Arithmetic Mean of the ROI for the R-rated movies is:", statistics.mean(roi))
print('10% Trimmed mean of the ROI of the r-rated movies is:',stats.trim_mean(roi, 0.10))

Arithmetic Mean of the ROI for the R-rated movies is: 59600710.27272727
10% Trimmed mean of the ROI of the r-rated movies is: 31883546.111111112


freq_demo = []
for i in roi:
    freq_demo.append((round(i, -6)))
print(freq_demo)#showing the freq_demo list

[350000000, 308000000, 24000000, 326000000, 316000000, 20000000, 82000000, 531000000, 13000000, 130000000, 55000000, 10000000, 9000000, 17000000, 27000000, 8000000, 318000000, 25000000, 23000000, 8000000, 24000000, 31000000, 45000000, 60000000, 12000000, 69000000, 4000000, 12000000, 13000000, 0, 53000000, 37000000, 17000000, 36000000, 20000000, 15000000, 14000000, 9000000, 8000000, 0, 4000000, 19000000, 13000000, 16000000, 4000000, 0, 0, 3000000, 49000000, 69000000, 15000000, 2000000, 1000000, 2000000, 2000000]


len(freq_demo)

55


freq_demo[-9] = 300000
freq_demo[-10] = 200000
freq_demo[-16] = 100000
freq_demo[-26] = 200000
freq_demo[1] = 300000000
freq_demo[4] = 300000000
freq_demo[3] = 350000000
freq_demo[16] = 300000000


freq_demo1 = Counter((freq_demo))
print(freq_demo1)#showing the freq_demo1 list

Counter({300000000: 3, 13000000: 3, 8000000: 3, 4000000: 3, 2000000: 3, 350000000: 2, 24000000: 2, 20000000: 2, 9000000: 2, 17000000: 2, 12000000: 2, 69000000: 2, 200000: 2, 15000000: 2, 82000000: 1, 531000000: 1, 130000000: 1, 55000000: 1, 10000000: 1, 27000000: 1, 25000000: 1, 23000000: 1, 31000000: 1, 45000000: 1, 60000000: 1, 53000000: 1, 37000000: 1, 36000000: 1, 14000000: 1, 100000: 1, 19000000: 1, 16000000: 1, 300000: 1, 3000000: 1, 49000000: 1, 1000000: 1})


freq_one = sorted(freq_demo1.items(), key=lambda i: i[0])
print(freq_one)#showing the freq_one list

[(100000, 1), (200000, 2), (300000, 1), (1000000, 1), (2000000, 3), (3000000, 1), (4000000, 3), (8000000, 3), (9000000, 2), (10000000, 1), (12000000, 2), (13000000, 3), (14000000, 1), (15000000, 2), (16000000, 1), (17000000, 2), (19000000, 1), (20000000, 2), (23000000, 1), (24000000, 2), (25000000, 1), (27000000, 1), (31000000, 1), (36000000, 1), (37000000, 1), (45000000, 1), (49000000, 1), (53000000, 1), (55000000, 1), (60000000, 1), (69000000, 2), (82000000, 1), (130000000, 1), (300000000, 3), (350000000, 2), (531000000, 1)]


roi_freq_amount = []
for i in freq_one: 
    roi_freq_amount.append(i[1])
print(roi_freq_amount)#showing the roi_freq_amount list

[1, 2, 1, 1, 3, 1, 3, 3, 2, 1, 2, 3, 1, 2, 1, 2, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 3, 2, 1]


len(roi_freq_amount)

36


roi_freq = []
for i in freq_one:
    roi_freq.append("${:,.0f}".format(i[0]))
print(roi_freq)#showing the roi_freq list

['$100,000', '$200,000', '$300,000', '$1,000,000', '$2,000,000', '$3,000,000', '$4,000,000', '$8,000,000', '$9,000,000', '$10,000,000', '$12,000,000', '$13,000,000', '$14,000,000', '$15,000,000', '$16,000,000', '$17,000,000', '$19,000,000', '$20,000,000', '$23,000,000', '$24,000,000', '$25,000,000', '$27,000,000', '$31,000,000', '$36,000,000', '$37,000,000', '$45,000,000', '$49,000,000', '$53,000,000', '$55,000,000', '$60,000,000', '$69,000,000', '$82,000,000', '$130,000,000', '$300,000,000', '$350,000,000', '$531,000,000']


len(roi_freq)

36


freq_dis_roi = pd.DataFrame({"Return On Investment (x)":roi_freq,
                                 "Frequency (f)":roi_freq_amount})


freq_dis_roi


def chunks(lst, n):
    """Yield successive n-sized chunks from lst."""
    for i in range(0, len(lst), n):
        yield lst[i:i + n]
        
a =list(chunks(range(70000, 350000000), 30000000))
a#showing the a list

[range(70000, 30070000),
 range(30070000, 60070000),
 range(60070000, 90070000),
 range(90070000, 120070000),
 range(120070000, 150070000),
 range(150070000, 180070000),
 range(180070000, 210070000),
 range(210070000, 240070000),
 range(240070000, 270070000),
 range(270070000, 300070000),
 range(300070000, 330070000),
 range(330070000, 350000000)]


vals = [70000,  30070000, 30070001,  60070001, 60070002,  90070002, 90070003,  120070003,
120070004,  150070004, 150070005,  180070005, 180070006, 210070006,  210070007,240070007, 240070008,
270070008,  270000009, 300070009, 300070010, 330070010, 330070011, 360070011, 360070012, 
        390070012, 390070013, 410070013, 410070014, 440007014, 440007015, 470007015, 470007016, 
        500070016,500070017, 530070017, 530070018, 560070019 ]


lower_vals = []
for i,x in enumerate(vals): 
    if (i%2) == 0:lower_vals.append("${:,.0f}".format(x)) 
print(lower_vals)#showing the lower_vals list

['$70,000', '$30,070,001', '$60,070,002', '$90,070,003', '$120,070,004', '$150,070,005', '$180,070,006', '$210,070,007', '$240,070,008', '$270,000,009', '$300,070,010', '$330,070,011', '$360,070,012', '$390,070,013', '$410,070,014', '$440,007,015', '$470,007,016', '$500,070,017', '$530,070,018']


len(lower_vals)

19


upper_vals = []
for i,x in enumerate(vals): 
    if (i%2) !=0: upper_vals.append("${:,.0f}".format(x))   
print(upper_vals)#showing the upper_vals list

['$30,070,000', '$60,070,001', '$90,070,002', '$120,070,003', '$150,070,004', '$180,070,005', '$210,070,006', '$240,070,007', '$270,070,008', '$300,070,009', '$330,070,010', '$360,070,011', '$390,070,012', '$410,070,013', '$440,007,014', '$470,007,015', '$500,070,016', '$530,070,017', '$560,070,019']


len(upper_vals)

19


count1 = 0
count2 = 0
count3 = 0
count4 = 0
count5 = 0
count6 = 0
count7 = 0
count8 = 0
count9 = 0
count10 = 0
count11 = 0
count12 = 0 
count13 = 0
count14 = 0
count15 = 0
count16 = 0
count17 = 0
count18 = 0
count19 = 0
for i in roi: 
    if 70000 <= i < 30070000:
        count1+=1
    if 30070001 <= i < 60070001:
        count2+=1
    if 60070002 <= i <= 90070002:
        count3+=1
    if 90070003 <= i <= 120070003:
        count4+=1
    if 120070004 <= i <= 150070004:
        count5+=1
    if 150070005 <= i <= 180070005:
        count6+=1
    if 180070006 <= i <= 210070006:
        count7+=1
    if 210070007 <= i <= 240070007:
        count8+=1
    if 240070008 <= i <= 270070008:
        count9+=1
    if 270070008 <= i <= 300070008:
        count10+=1
    if 300070008 <= i <= 330070008:
        count11+=1
    if 330070008 <= i <= 360070008:
        count12+=1
    if 360070009 <= i <= 390070009:
        count13+=1
    if 390070010 <= i <= 410070010:
        count14+=1
    if 410070011 <= i <= 440070011:
        count15+=1
    if 440070012 <= i <= 470070012:
        count16+=1
    if 470070013 <= i <= 500070013:
        count17+=1
    if 530070014 <= i <= 530070015:
        count18+=1
    if 530070016 <= i <= 570070017:
        count19+=1
freq_amount = [count1,count2,count3,count4,count5,count6,count7,
               count8,count9,count10,count11,count12, 
               count13,count14,count15,count16,count17,count18,count19]
print(freq_amount)#showing the freq_amount list

[37, 7, 4, 0, 1, 0, 0, 0, 0, 0, 4, 1, 0, 0, 0, 0, 0, 0, 1]


len(freq_amount)

19


freq_amount_percent_demo = [count1/55*100,count2/55*100,count3/55*100,count4/55*100,
                       count5/55*100,count6/55*100,count7/55*100,count8/55*100,
                       count9/55*100, count10/55*100, count11/55*100, count12/55*100,
                count13/55*100,count14/55*100,count15/55*100,count16/55*100,
                       count17/55*100,count18/55*100,count19/55*100,]

freq_amount_percent_demo1 = [67, 13, 8, 0, 2, 0, 0, 0, 0, 0, 7, 2,
                            0, 0, 0, 0, 0, 0, 2]
print(freq_amount_percent_demo1)#showing the freq_amount_percent_demo1 list

[67, 13, 8, 0, 2, 0, 0, 0, 0, 0, 7, 2, 0, 0, 0, 0, 0, 0, 2]


len(freq_amount_percent_demo1)

19


freq_amount_percent = []
for i in freq_amount_percent_demo1:
    freq_amount_percent.append("{:}%".format(i))
print(freq_amount_percent)#showing the freq_amount_percent list

['67%', '13%', '8%', '0%', '2%', '0%', '0%', '0%', '0%', '0%', '7%', '2%', '0%', '0%', '0%', '0%', '0%', '0%', '2%']


len(freq_amount_percent)

19


freq_cumulative_amount = Cumulative(freq_amount)
print(freq_cumulative_amount)#showing the freq_cumulative_amount list

[37, 44, 48, 48, 49, 49, 49, 49, 49, 49, 53, 54, 54, 54, 54, 54, 54, 54, 55]


len(freq_cumulative_amount)

19


freq_cumulative_percent_demo = Cumulative(freq_amount_percent_demo1)
print(freq_cumulative_percent_demo)#showing the freq_cumulative_percent_demo list

[67, 80, 88, 88, 90, 90, 90, 90, 90, 90, 97, 99, 99, 99, 99, 99, 99, 99, 101]


len(freq_cumulative_percent_demo)

19


freq_cumulative_percent = []
for i in freq_cumulative_percent_demo:
    freq_cumulative_percent.append("{:}%".format(i))
print(freq_cumulative_percent)#showing the freq_cumulative_percent list

['67%', '80%', '88%', '88%', '90%', '90%', '90%', '90%', '90%', '90%', '97%', '99%', '99%', '99%', '99%', '99%', '99%', '99%', '101%']


len(freq_cumulative_percent)

19


freq_cum_dis1 = pd.DataFrame({"Lower\nValue":lower_vals,
                             "Upper\nValue":upper_vals,
                             "Frequency (f)":freq_amount,
                             "Percentage (%)":freq_amount_percent,
                            "Cumulative\nFrequency":freq_cumulative_amount,
                            "Cumulative\nPercentage":freq_cumulative_percent})


freq_cum_dis1


count1 = 0
count2 = 0
count3 = 0
count4 = 0
count5 = 0
count6 = 0
count7 = 0
count8 = 0
count9 = 0
count10 = 0
count11 = 0
count12 = 0
count13 = 0
for i in roi: 
    if i < 30000000:
        count1+=1
    if 30000000 <= i < 60000000:
        count2+=1
    if 60000000 <= i < 90000000:
        count3+=1
    if 90000000 <= i < 120000000:
        count4+=1
    if 120000000 <= i < 150000000:
        count5+=1
    if 150000000 <= i < 180000000:
        count6+=1
    if 180000000 <= i < 210000000:
        count7+=1
    if 210000000 <= i < 240000000:
        count8+=1
    if 240000000 <= i < 270000000:
        count9+=1
    if 270000000 <= i < 300000000:
        count10+=1
    if 300000000 <= i <= 330000000:
        count11+=1
    if 330000000 <= i <= 360000000:
        count12+=1
    if i > 360000000:
        count13+=1
freq_amount = [count1,count2,count3,count4,count5,count6,count7,
               count8,count9,count10,count11,count12, count13]
print(freq_amount)#showing the freq_amount list

[37, 7, 4, 0, 1, 0, 0, 0, 0, 0, 4, 1, 1]


len(freq_amount)

13


cum_rel_freq_demo = []
for i in freq_amount:cum_rel_freq_demo.append(i/55*100)
cum_rel_freq_demo1 = [67,13,7,0,2,0,0,0,0,0,7,2,2]
print(cum_rel_freq_demo1)#showing the cum_rel_freq_demo1 list

[67, 13, 7, 0, 2, 0, 0, 0, 0, 0, 7, 2, 2]


len(cum_rel_freq_demo1)

13


cum_rel_freq_demo2 = Cumulative(cum_rel_freq_demo1)
print(cum_rel_freq_demo2)#showing the cum_rel_freq_demo2 list

[67, 80, 87, 87, 89, 89, 89, 89, 89, 89, 96, 98, 100]


len(cum_rel_freq_demo2)

13


cum_rel_freq_percent = []
for i in cum_rel_freq_demo2:
    cum_rel_freq_percent.append("{:}%".format(i))
print(cum_rel_freq_percent)#showing the cum_rel_freq_percent list

['67%', '80%', '87%', '87%', '89%', '89%', '89%', '89%', '89%', '89%', '96%', '98%', '100%']


len(cum_rel_freq_percent)

13


freq_cumulative_amount = Cumulative(freq_amount)
print(freq_cumulative_amount)#showing the freq_cumulative_amount list

[37, 44, 48, 48, 49, 49, 49, 49, 49, 49, 53, 54, 55]


len(freq_cumulative_amount)

13


intervals_cum = [ '< $30 Million','30 to < $60 Million','60 to < $90 Million',
                 '90 to < $120 Million','120 < $150 Million',
 '150 to < $180 Miilion', '180 to < $210 Miilion', '210 to < $240 Miilion',
                 '240 to < $270 Miilion',
 '270 to < $300 Miilion','300 to < $330 Million','330 to < $360 Million','>= $360 Miilion']
print(intervals_cum)#showing the intervals_cum list

['< $30 Million', '30 to < $60 Million', '60 to < $90 Million', '90 to < $120 Million', '120 < $150 Million', '150 to < $180 Miilion', '180 to < $210 Miilion', '210 to < $240 Miilion', '240 to < $270 Miilion', '270 to < $300 Miilion', '300 to < $330 Million', '330 to < $360 Million', '>= $360 Miilion']


len(intervals_cum)

13


cum_rel_freq1 = pd.DataFrame({"Return On Investment":intervals_cum,
                             "Frequency (f)":freq_amount,
                             "Cumulative Frequency":freq_cumulative_amount,
                             "Cumelative Relative Frequency Percentage":cum_rel_freq_percent,
                            })


cum_rel_freq1


means = '59,600,710'
std = '111,311,472'

def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():
    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-350, 350)
    m = [60]
    s = [111]
    c = ['#ff5500']


    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")

   
    plt.xlim(-350, 350)
    plt.ylim(0, .2)
    plt.legend(fontsize=11)
    plt.title('Variability of ROI of R-rated Movies\n Normal Distribution, Mean =16.4 million, StDev=21 million',fontsize=14)
    plt.xlabel("ROI of R-rated Movies",fontsize=14)
    plt.ylabel("Density",fontsize=14)
    plt.grid(False)
    plt.show()

if __name__ == '__main__':
   main()


#plt.ylim(-1,2.1) # Setting y limits so the axis are consistent
#plt.figure(figsize=(8,5))
plt.ylabel('ROI of R-rated Movies',fontsize=14)
plt.xlabel('Ranking of Values',fontsize=14)
plt.title("The Variance of all the ROI\n of all the R-rated movies in the Drama genre",fontsize=14) # Setting the title 
plt.scatter(x=df_roi_r.index, y=df_roi_r['ROI'], s=15, color='#ff5500'); # Plotting the scatter
plt.hlines(y=df_roi_r['ROI'].mean(), xmin=0, xmax=55, color='blue') # Mean line
plt.grid(False)
plt.show()# Telling matplotlib to show the chart


#plt.ylim(-1,2.1) # Setting y limits so the axis are consistent
#plt.figure(figsize=(8,5))
plt.ylabel('ROI of R-rated Movies',fontsize=14)
plt.xlabel('Position of Values',fontsize=14)
plt.title("The Variance of all the ROI\n of all the R-rated movies in the Drama genre",fontsize=14) # Setting the title 
plt.scatter(x=df_roi_r.index, y=df_roi_r['ROI'], s=15, color='#ff5500'); # Plotting the scatter
plt.hlines(y=df_roi_r['ROI'].mean(), xmin=0, xmax=55, color='blue') # Mean line

for std_int in [-2, -1, 1, 2]: # Going through different stds from the mean
    standard_deviation = df_roi_r['ROI'].mean() + df_roi_r['ROI'].std()*std_int
    
    plt.hlines(y=standard_deviation,
               xmin=0,
               xmax=55,
               linestyles='dashed',
               colors='green'); # 1 std above
    
    # Giving labels to the lines we just drew
    plt.text(y=standard_deviation + 2, x=-10, s=std_int, ha='center')
    plt.grid(False)


import matplotlib.pyplot as plt

# An "interface" to matplotlib.axes.Axes.hist() method
n, bins, patches = plt.hist(x=roi, bins='auto', color='#ff5500',
                            alpha=0.7, rwidth=0.85)
plt.grid(False)
plt.grid(axis='y', alpha=0.75)
plt.xlabel('ROI of R-rated Movies',fontsize=14)
plt.ylabel('Frequency',fontsize=14)
#plt.text( x=np.min(cost), y=0.1, s=r'$\mu=16 million, b=20 million$')
plt.title('The Pearson’s Coefficient of Skewness for the ROI\n of all R-rated movies is 1.14 (n=55)',fontsize=14)

Text(0.5, 1.0, 'The Pearson’s Coefficient of Skewness for the ROI\n of all R-rated movies is 1.14 (n=55)')


# An "interface" to matplotlib.axes.Axes.hist() method
median_roi = statistics.median(roi)
mean_roi = 59600710
mode_roi = statistics.mode(roi)
n, bins, patches = plt.hist(x=roi, bins='auto', color='#ff5500',
                            alpha=0.2, rwidth=0.85)
plt.grid(axis='y', alpha=0.75)
names = ["median", "mean", "mode"]
colors = ['green', 'red', 'blue']
measurements = [median_roi, mean_roi, mode_roi]
for measurement, name, color in zip(measurements, names, colors):
    plt.axvline(x=measurement,  linestyle='--', linewidth=2.5, label='{0} at {1}'.format(name, measurement), c=color)
plt.legend(fontsize=10);
plt.title('Comparison of Mode, Median and Mean \nin the Distribution of the ROI of all the R-rated Drama movies',fontsize=14)

Text(0.5, 1.0, 'Comparison of Mode, Median and Mean \nin the Distribution of the ROI of all the R-rated Drama movies')


means = '59,600,710'
std = '111,311,472'
means1 = 60
std1 = 111
def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():

    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-400, 400)
    s = [111]
    m = [60]
    c = ['#ff5500']

    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")
    
    x = np.linspace(means1 - std1*2, means1 + std1*2)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x, y, alpha=0.5, color='#ff5500')
    ax.annotate('at least 75%\n at least 41 obs', xy=(250,0.0035), xytext=(250,0.0020),
            arrowprops={'arrowstyle': '-|>'}, va='center', color='black',fontsize=11)
    
   
    plt.xlim(-400, 400)
    plt.ylim(0, .004)
    plt.legend(fontsize=10)
    plt.title('Chebyshevs Theorem on the ROI \nof the R-rated Movies in the Drama Genre (n=55)',fontsize=14)
    plt.xlabel("ROI of R-rated Movies",fontsize=14)
    plt.ylabel("Density", fontsize=14)
    plt.show()

if __name__ == '__main__':
   main()


means = '59,600,710'
std = '111,311,472'
means1 = 60
std1 = 111
def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():
    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-400, 400)
    s = [111]
    m = [60]
    c = ['#ff5500']

    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")
    
    x = np.linspace(280, 350)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x, y, alpha=0.5, color='#ff5500')
    
    x1 = np.linspace(-170, -250)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x1, y, alpha=0.5, color='#ff5500')

    ax.annotate('at least 13.9%\n at leat 8 obs',xy=(250,0.0035), xytext=(250,0.0020),
            arrowprops={'arrowstyle': '-|>'}, va='center', color='black',fontsize=11)
   
    plt.xlim(-400, 400)
    plt.ylim(0, .004)
    plt.legend(fontsize=10)
    plt.title('Chebyshevs Theorem on the ROI \nof the R-rated Movies in the Drama Genre (n=55)',fontsize=14)
    plt.xlabel("ROI of R-rated Movies",fontsize=14)
    plt.ylabel("Density",fontsize=14)
    plt.show()

if __name__ == '__main__':
   main()


import seaborn as sns
sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.stripplot(data=df_roi_r, color='#ff5500');
sns.violinplot( data=df_roi_r,inner=None,color='0.8').set(title='KDE and Jittered strip plot\n on the ROI of the r-rated movies')
plt.show()


sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.swarmplot(data=df_roi_r, color='#ff5500');
sns.violinplot( data=df_roi_r, color='0.8', inner=None, aplha=.2).set(title='KDE and swarm plot\n on the ROI of the r-rated movies')
#sns.despine()
plt.show()


sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.stripplot(data=df_roi_r, color='#ff5500', jitter=False)
sns.violinplot(data=df_roi_r,  split=True,inner=None,
      scale="count", color='0.8', alpha=.1).set(title='KDE and rug plot\n on the ROI of the r-rated movies')
#sns.despine()
plt.show()


freq_dis_roi1 = freq_dis_roi[:12].style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_3504\1533880768.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_dis_roi1 = freq_dis_roi[:12].style.hide_index()\


dfi.export(freq_dis_roi1, 'freq_dis_roi1.png')


freq_dis_roi2 = freq_dis_roi[12:24].style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_3504\2751053211.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_dis_roi2 = freq_dis_roi[12:24].style.hide_index()\


dfi.export(freq_dis_roi2, 'freq_dis_roi2.png')


freq_dis_roi3 = freq_dis_roi[24:].style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_3504\3066803151.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_dis_roi3 = freq_dis_roi[24:].style.hide_index()\


dfi.export(freq_dis_roi3, 'freq_dis_roi3.png')


freq_cum_dis11 = freq_cum_dis1.style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black"),
                                      ("font-size", "10pt")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\3430443440.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_cum_dis11 = freq_cum_dis1.style.hide_index()\


dfi.export(freq_cum_dis11, 'freq_cum_dis11.png')


cum_rel_freq11 = cum_rel_freq1.style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black"),
                                      ("font-size", "10pt")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_3504\906232283.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  cum_rel_freq11 = cum_rel_freq1.style.hide_index()\


dfi.export(cum_rel_freq11, 'cum_rel_freq11.png')


amount = [30000000, 60000000, 90000000, 120000000, 150000000, 180000000, 210000000, 240000000, 
       270000000, 300000000, 330000000, 360000000, 531000000]
freq = [67, 80, 87, 87, 89, 89, 89, 89, 89, 89, 96, 98, 100]
  
plt.plot( amount, freq ,color='red', marker='o')
plt.title('Cumulative relative frequency (%) of \n the ROI made on R-rated movies', fontsize=14)
plt.xlabel('Return On Investment', fontsize=14)
plt.ylabel('Cumulative relative frequency (%)', fontsize=14)
plt.grid(True)
plt.show()


roi_per = []
for i in system_rating_r["ROI Percentage"]:
    i = int(i.replace('%', ''))
    roi_per.append(i)
print(roi_per) #showing the roi_per list

[350, 504, 40, 593, 575, 36, 156, 1327, 35, 418, 238, 44, 38, 81, 133, 41, 2448, 195, 179, 65, 199, 263, 411, 601, 132, 815, 54, 250, 258, 5, 1332, 1056, 501, 1081, 675, 731, 707, 465, 408, 4, 216, 970, 850, 1557, 444, 16, 218, 2670, 813, 808, 74, 1852, 21, 13, 22]


len(roi_per)

55


df_roi_per_r = pd.DataFrame({"ROI Percentage":roi_per})


df_roi_per_r


x = statistics.mean(roi_per)
print("Arithmetic Mean of the ROI for the R-rated movies is:", x)

Arithmetic Mean of the ROI for the R-rated movies is: 508.8727272727273


print("Median of the ROI for the R-rated movies is:", statistics.median(roi_per))

Median of the ROI for the R-rated movies is: 263


print("Standard deviation of the  ROI Percentage for the R-rated movies is:", np.std(roi_per, ddof=1))

Standard deviation of the  ROI Percentage for the R-rated movies is: 590.4479797873956


cv = lambda x: np.std(x, ddof=1) / np.mean(x) * 100
print("Coefficient of Variation of the  ROI Percentage for the R-rated movies is:", cv(roi_per))

Coefficient of Variation of the  ROI Percentage for the R-rated movies is: 116.03058056419451


def pearsons(mean, median, standard_deviation):
    skewness = (mean-median)*3/standard_deviation
    return skewness
print("Pearson’s Coefficient of Skewness of the ROI Percentage for the R-rated movies is:", 
      pearsons( statistics.mean(roi_per),statistics.median(roi_per),np.std(roi_per, ddof=1)))

Pearson’s Coefficient of Skewness of the ROI Percentage for the R-rated movies is: 1.2492517665718463


def chebyshevs(mean, standard_deviation, num_std, previous_p):
    position_std = num_std*standard_deviation
    upper_range = mean - position_std 
    if upper_range < 0: upper_range = 0
    lower_range = position_std + mean
    if num_std == 2: 
        print('At least 75% of the ROI Percentage of the r-rated movies ranges from',upper_range,'to',lower_range)
    if num_std == 3: 
        print('At least 13.9% of the ROI Percentage of the r-rated movies ranges from',previous_p,'to',lower_range)
chebyshevs(510, 590, 2, 0)
chebyshevs(510, 590, 3, 1690)

At least 75% of the ROI Percentage of the r-rated movies ranges from 0 to 1690
At least 13.9% of the ROI Percentage of the r-rated movies ranges from 1690 to 2280


print('Kurtosis of the ROI Percentage of the r-rated movies is:',kurtosis(roi_per, fisher=False))
print('Excess Kurtosis of the ROI Percentage of the r-rated movies is:',
      (kurtosis(roi_per,fisher=False)-3))#leptokurtic

Kurtosis of the ROI Percentage of the r-rated movies is: 6.600168491255548
Excess Kurtosis of the ROI Percentage of the r-rated movies is: 3.6001684912555483


print("Arithmetic Mean of the ROI for the R-rated movies is:", statistics.mean(roi_per))
print('10% Trimmed mean of the ROI of the r-rated movies is:',stats.trim_mean(roi_per, 0.10))

Arithmetic Mean of the ROI for the R-rated movies is: 508.8727272727273
10% Trimmed mean of the ROI of the r-rated movies is: 401.55555555555554


freq_demo = [5, 5, 10, 20, 20, 20, 40, 40, 40, 40, 40, 40, 50, 70, 70, 80, 130, 130,
            150, 180, 200, 220, 240, 300, 300, 300, 400, 400, 400, 400, 500, 500, 500, 
            500, 600, 600, 600, 700, 700, 700, 800, 800, 800, 900, 1000, 1100, 1300, 
            1300, 2000, 2000, 2500, 3000]
print(freq_demo) #showing the freq_demo list

[5, 5, 10, 20, 20, 20, 40, 40, 40, 40, 40, 40, 50, 70, 70, 80, 130, 130, 150, 180, 200, 220, 240, 300, 300, 300, 400, 400, 400, 400, 500, 500, 500, 500, 600, 600, 600, 700, 700, 700, 800, 800, 800, 900, 1000, 1100, 1300, 1300, 2000, 2000, 2500, 3000]


len(freq_demo)

52


freq_demo1 = Counter((freq_demo))
print(freq_demo1)#showing the freq_demo1 list

Counter({40: 6, 400: 4, 500: 4, 20: 3, 300: 3, 600: 3, 700: 3, 800: 3, 5: 2, 70: 2, 130: 2, 1300: 2, 2000: 2, 10: 1, 50: 1, 80: 1, 150: 1, 180: 1, 200: 1, 220: 1, 240: 1, 900: 1, 1000: 1, 1100: 1, 2500: 1, 3000: 1})


freq_one = sorted(freq_demo1.items(), key=lambda i: i[0])
print(freq_one)#showing the freq_one list

[(5, 2), (10, 1), (20, 3), (40, 6), (50, 1), (70, 2), (80, 1), (130, 2), (150, 1), (180, 1), (200, 1), (220, 1), (240, 1), (300, 3), (400, 4), (500, 4), (600, 3), (700, 3), (800, 3), (900, 1), (1000, 1), (1100, 1), (1300, 2), (2000, 2), (2500, 1), (3000, 1)]


roi_per_freq = []
for i in freq_one: 
    roi_per_freq.append("{:}%".format(i[0]))
print(roi_per_freq)#showing the roi_per_freq list

['5%', '10%', '20%', '40%', '50%', '70%', '80%', '130%', '150%', '180%', '200%', '220%', '240%', '300%', '400%', '500%', '600%', '700%', '800%', '900%', '1000%', '1100%', '1300%', '2000%', '2500%', '3000%']


len(roi_per_freq)

26


roi_per_freq_amount = []
for i in freq_one: 
    roi_per_freq_amount.append(i[1])
print(roi_per_freq_amount)#showing the roi_per_freq_amount list

[2, 1, 3, 6, 1, 2, 1, 2, 1, 1, 1, 1, 1, 3, 4, 4, 3, 3, 3, 1, 1, 1, 2, 2, 1, 1]


len(roi_per_freq_amount)

26


freq_dis3 = pd.DataFrame({"ROI\nPercentage (x)":roi_per_freq,
                                 "Frequency (f)":roi_per_freq_amount})


freq_dis3


def chunks(lst, n):
    """Yield successive n-sized chunks from lst."""
    for i in range(0, len(lst), n):
        yield lst[i:i + n]
        
#a =list(chunks(range(0, 2700), 150))
a =list(chunks(range(0, 2800), 200))
a#showing the a list

[range(0, 200),
 range(200, 400),
 range(400, 600),
 range(600, 800),
 range(800, 1000),
 range(1000, 1200),
 range(1200, 1400),
 range(1400, 1600),
 range(1600, 1800),
 range(1800, 2000),
 range(2000, 2200),
 range(2200, 2400),
 range(2400, 2600),
 range(2600, 2800)]


lower_val = ['0%', '151%', '302%', '453%', '604%', '755%', '906%', '1057%', '1208%', '1359%', 
            '1510%', '1661%', '1812%', '1963%', '2114%', '2265%', '2416%', '2567%' ]
print(lower_val)#showing the lower_val list

['0%', '151%', '302%', '453%', '604%', '755%', '906%', '1057%', '1208%', '1359%', '1510%', '1661%', '1812%', '1963%', '2114%', '2265%', '2416%', '2567%']


len(lower_val)

18


upper_val = ['150%', '301%', '452%', '603%', '754%', '905%', '1056%', '1207%','1358%', '1509%',
            '1660%', '1811%', '1962%', '2113%', '2264%', '2415%', '2566%', '2717%']
print(upper_val)#showing the upper_val list

['150%', '301%', '452%', '603%', '754%', '905%', '1056%', '1207%', '1358%', '1509%', '1660%', '1811%', '1962%', '2113%', '2264%', '2415%', '2566%', '2717%']


len(upper_val)

18


count1 = 0
count2 = 0
count3 = 0
count4 = 0
count5 = 0
count6 = 0
count7 = 0
count8 = 0
count9 = 0
count10 = 0
count11 = 0
count12 = 0
count13 = 0
count14 = 0
count15 = 0
count16 = 0
count17 = 0
count18 = 0
for i in roi_per: 
    if 0 <= i <= 150:
        count1+=1
    if 151 <= i <= 301:
        count2+=1
    if 302 <= i <= 452:
        count3+=1
    if 453 <= i <= 603:
        count4+=1
    if 604 <= i <= 754:
        count5+=1
    if 755 <= i <= 905:
        count6+=1
    if 906 <= i <= 1056:
        count7+=1
    if 1057 <= i <= 1207:
        count8+=1
    if 1208 <= i <= 1358:
        count9+=1
    if 1359 <= i <= 1509:
        count10+=1
    if 1510 <= i <= 1660:
        count11+=1
    if 1661 <= i <= 1811:
        count12+=1
    if 1812 <= i <= 1962:
        count13+=1
    if 1963 <= i <= 2113:
        count14+=1
    if 2114 <= i <= 2264:
        count15+=1
    if 2265 <= i <= 2415:
        count16+=1
    if 2416 <= i <= 2566:
        count17+=1
    if 2567 <= i <= 2717:
        count18+=1

freq_amount = [count1,count2,count3,count4,count5,count6,count7,count8,count9,count10,
              count11,count12,count13,count14,count15,count16,count17,count18]
print(freq_amount)#showing the freq_amount list

[18, 10, 5, 6, 3, 4, 2, 1, 2, 0, 1, 0, 1, 0, 0, 0, 1, 1]


len(freq_amount)

18


freq_amount_percent_demo = [count1/55*100,count2/55*100,count3/55*100,count4/55*100,
                       count5/55*100,count6/55*100,count7/55*100,count8/55*100,
                       count9/55*100,count10/55*100,count11/55*100,count12/55*100,
                       count13/55*100,count14/55*100,count15/55*100,count16/55*100,
                       count17/55*100,count18/55*100,]
freq_amount_percent_demo1 = [33, 18, 9, 11, 5, 7, 3, 2, 4, 0, 2, 0, 2, 0, 0, 0, 2, 2]
print(freq_amount_percent_demo1)#showing the freq_amount_percent_demo1 list

[33, 18, 9, 11, 5, 7, 3, 2, 4, 0, 2, 0, 2, 0, 0, 0, 2, 2]


len(freq_amount_percent_demo1)

18


freq_amount_percent = []
for i in freq_amount_percent_demo1:
    freq_amount_percent.append("{:}%".format(i))
print(freq_amount_percent)#showing the freq_amount_percent list

['33%', '18%', '9%', '11%', '5%', '7%', '3%', '2%', '4%', '0%', '2%', '0%', '2%', '0%', '0%', '0%', '2%', '2%']


len(freq_amount_percent)

18


freq_cumulative_amount = Cumulative(freq_amount)
print(freq_cumulative_amount)#showing the freq_cumulative_amount list

[18, 28, 33, 39, 42, 46, 48, 49, 51, 51, 52, 52, 53, 53, 53, 53, 54, 55]


len(freq_cumulative_amount)

18


freq_cumulative_percent_demo = Cumulative(freq_amount_percent_demo1)
print(freq_cumulative_percent_demo)#showing the freq_cumulative_percent_demo list

[33, 51, 60, 71, 76, 83, 86, 88, 92, 92, 94, 94, 96, 96, 96, 96, 98, 100]


len(freq_cumulative_percent_demo)

18


freq_cumulative_percent = []
for i in freq_cumulative_percent_demo:
    freq_cumulative_percent.append("{:}%".format(i))
print(freq_cumulative_percent)#showing the freq_cumulative_percent list

['33%', '51%', '60%', '71%', '76%', '83%', '86%', '88%', '92%', '92%', '94%', '94%', '96%', '96%', '96%', '96%', '98%', '100%']


len(freq_cumulative_percent)

18


freq_cum_dis2 = pd.DataFrame({"Lower\nValue":lower_val,
                             "Upper\nValue":upper_val,
                             "Frequency (f)":freq_amount,
                             "Percentage (%)":freq_amount_percent,
                            "Cumulative\nFrequency":freq_cumulative_amount,
                            "Cumulative\nPercentage":freq_cumulative_percent})


freq_cum_dis2


count1 = 0
count2 = 0
count3 = 0
count4 = 0
count5 = 0
count6 = 0
count7 = 0
count8 = 0
count9 = 0
count10 = 0
count11 = 0
count12 = 0
count13 = 0
count14 = 0
for i in roi_per: 
    if i < 200:
        count1+=1
    if 200 <= i < 400:
        count2+=1
    if 400 <= i < 600:
        count3+=1
    if 600 <= i < 800:
        count4+=1
    if 800 <= i < 1000:
        count5+=1
    if 1000 <= i < 1200:
        count6+=1
    if 1200 <= i < 1400:
        count7+=1
    if 1400 <= i < 1600:
        count8+=1
    if 1600 <= i < 1800:
        count9+=1
    if 1800 <= i <= 2000:
        count10+=1
    if 2000 <= i < 2200:
        count11+=1
    if 2200 <= i < 2400:
        count12+=1
    if 2400 <= i < 2600:
        count13+=1
    if 2600 <= i <= 2800:
        count14+=1
freq_amount = [count1,count2,count3,count4,count5,count6,count7,count8,count9,count10,
              count11,count12,count13,count14]
print(freq_amount)#showing the freq_amount list

[22, 7, 9, 4, 5, 2, 2, 1, 0, 1, 0, 0, 1, 1]


len(freq_amount)

14


cum_rel_freq_demo = []
for i in freq_amount:cum_rel_freq_demo.append(i/55*100)
cum_rel_freq_demo1 = [40,13,16,7,9,4,3,2,0,2,0,0,2,2]
print(cum_rel_freq_demo1)#showing the cum_rel_freq_demo1 list

[40, 13, 16, 7, 9, 4, 3, 2, 0, 2, 0, 0, 2, 2]


len(cum_rel_freq_demo1)

14


cum_rel_freq_demo2 = Cumulative(cum_rel_freq_demo1)
print(cum_rel_freq_demo2)#showing the cum_rel_freq_demo2 list

[40, 53, 69, 76, 85, 89, 92, 94, 94, 96, 96, 96, 98, 100]


len(cum_rel_freq_demo2)

14


cum_rel_freq_percent = []
for i in cum_rel_freq_demo2:
    cum_rel_freq_percent.append("{:}%".format(i))
print(cum_rel_freq_percent)#showing the cum_rel_freq_percent list

['40%', '53%', '69%', '76%', '85%', '89%', '92%', '94%', '94%', '96%', '96%', '96%', '98%', '100%']


len(cum_rel_freq_percent)

14


freq_cumulative_amount = Cumulative(freq_amount)
print(freq_cumulative_amount)#showing the freq_cumulative_amount list

[22, 29, 38, 42, 47, 49, 51, 52, 52, 53, 53, 53, 54, 55]


len(freq_cumulative_amount)

14


intervals_cum = [ '< 200%','200% to < 400%','400% to < 600%','600% to < 800%','800% < 1000%',
 '1000% to < 1200%', '1200% to < 1400%', '1400% to < 1600%','1600% to < 1800%',
 '1800% to < 2000%','2000% to < 2200%','2200% to < 2400%','2400% to < 2600%', '>= 2800%']
print(intervals_cum)#showing the intervals_cum list

['< 200%', '200% to < 400%', '400% to < 600%', '600% to < 800%', '800% < 1000%', '1000% to < 1200%', '1200% to < 1400%', '1400% to < 1600%', '1600% to < 1800%', '1800% to < 2000%', '2000% to < 2200%', '2200% to < 2400%', '2400% to < 2600%', '>= 2800%']


len(intervals_cum)

14


cum_rel_freq2 = pd.DataFrame({"Return On Investment":intervals_cum,
                             "Frequency (f)":freq_amount,
                             "Cumulative Frequency":freq_cumulative_amount,
                             "Cumelative Relative Frequency Percentage":cum_rel_freq_percent,
                            })


cum_rel_freq2


means = '510%'
std = '590%'

def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():
    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-40, 40)
    s = [5.9]
    m = [5.1]
    c = ['#ff5500']


    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")

   
    plt.xlim(-40, 40)
    plt.ylim(0, .2)
    plt.legend(fontsize=11)
    plt.title('Variability of ROI Percentage of R-rated Movies\n Normal Distribution, Mean = 510%, StDev=590%',fontsize=14)
    plt.xlabel("ROI Percentage of R-rated Movies",fontsize=14)
    plt.ylabel("Density",fontsize=14)
    plt.grid(False)
    plt.show()

if __name__ == '__main__':
   main()


#plt.ylim(-1,2.1) # Setting y limits so the axis are consistent
#plt.figure(figsize=(8,5))
plt.ylabel('ROI Percentage of R-rated Movies',fontsize=14)
plt.xlabel('Ranking of Values',fontsize=14)
plt.title("The Variance of all the ROI Percentage\n of all the R-rated movies in the Drama genre",fontsize=14) # Setting the title 
plt.scatter(x=df_roi_r.index, y=df_roi_r['ROI Percentage'], s=15, color='#ff5500'); # Plotting the scatter
plt.hlines(y=df_roi_r['ROI Percentage'].mean(), xmin=0, xmax=55, color='blue') # Mean line
plt.grid(False)
plt.show()# Telling matplotlib to show the chart


#plt.ylim(-1,2.1) # Setting y limits so the axis are consistent
#plt.figure(figsize=(8,5))
plt.ylabel('ROI Perecntage of R-rated Movies',fontsize=14)
plt.xlabel('Position of Values',fontsize=14)
plt.title("The Variance of all the ROI Percentage\n of all the R-rated movies in the Drama genre",fontsize=14) # Setting the title 
plt.scatter(x=df_roi_r.index, y=df_roi_r['ROI Percentage'], s=15, color='#ff5500'); # Plotting the scatter
plt.hlines(y=df_roi_r['ROI Percentage'].mean(), xmin=0, xmax=55, color='blue') # Mean line

for std_int in [-2, -1, 1, 2]: # Going through different stds from the mean
    standard_deviation = df_roi_r['ROI Percentage'].mean() + df_roi_r['ROI Percentage'].std()*std_int
    
    plt.hlines(y=standard_deviation,
               xmin=0,
               xmax=55,
               linestyles='dashed',
               colors='green'); # 1 std above
    
    # Giving labels to the lines we just drew
    plt.text(y=standard_deviation + 2, x=-10, s=std_int, ha='center')
    plt.grid(False)


import matplotlib.pyplot as plt

# An "interface" to matplotlib.axes.Axes.hist() method
n, bins, patches = plt.hist(x=roi_per, bins='auto', color='#ff5500',
                            alpha=0.7, rwidth=0.85)
plt.grid(False)
plt.grid(axis='y', alpha=0.75)
plt.xlabel('ROI Percentage of R-rated Movies',fontsize=14)
plt.ylabel('Frequency',fontsize=14)
#plt.text( x=np.min(cost), y=0.1, s=r'$\mu=16 million, b=20 million$')
plt.title('The Pearson’s Coefficient of Skewness for the ROI Percentage\n of all R-rated movies is 1.24 (n=55)',fontsize=14)

Text(0.5, 1.0, 'The Pearson’s Coefficient of Skewness for the ROI Percentage\n of all R-rated movies is 1.24 (n=55)')


# An "interface" to matplotlib.axes.Axes.hist() method
median_roi_per = statistics.median(roi_per)
mean_roi_per = 510
mode_roi_per = statistics.mode(roi_per)
n, bins, patches = plt.hist(x=roi_per, bins='auto', color='#ff5500',
                            alpha=0.2, rwidth=0.85)
plt.grid(axis='y', alpha=0.75)
names = ["median", "mean", "mode"]
colors = ['green', 'red', 'blue']
measurements = [median_roi_per, mean_roi_per, mode_roi_per]
for measurement, name, color in zip(measurements, names, colors):
    plt.axvline(x=measurement,  linestyle='--', linewidth=2.5, label='{0} at {1}'.format(name, measurement), c=color)
plt.legend(fontsize=10);
plt.title('Comparison of Mode, Median and Mean in the Distribution\n of the ROI Percentage of all the R-rated Drama movies',fontsize=14)

Text(0.5, 1.0, 'Comparison of Mode, Median and Mean in the Distribution\n of the ROI Percentage of all the R-rated Drama movies')


means = '510%'
std = '590%'
means1 = 5.1
std1 = 5.9
def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():

    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-50, 50)
    s = [5.9]
    m = [5.1]
    c = ['#ff5500']

    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")
    
    x = np.linspace(means1 - std1*2, means1 + std1*2)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x, y, alpha=0.5, color='#ff5500')
    ax.annotate('at least 75%\n at least 41 obs', xy=(250,0.0035), xytext=(250,0.0020),
            arrowprops={'arrowstyle': '-|>'}, va='center', color='black',fontsize=11)
    
   
    plt.xlim(-50, 50)
    plt.ylim(0, .07)
    plt.legend(fontsize=10)
    plt.title('Chebyshevs Theorem on the ROI Percentage\nof the R-rated Movies in the Drama Genre (n=55)',fontsize=14)
    plt.xlabel("ROI Percentage of R-rated Movies",fontsize=14)
    plt.ylabel("Density", fontsize=14)
    plt.show()

if __name__ == '__main__':
   main()


means = '510%'
std = '590%'
means1 = 5.1
std1 = 5.9
def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():
    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-40, 40)
    s = [5.9]
    m = [5.1]
    c = ['#ff5500']

    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2, label=f"$\mu={means}$\n$\sigma={std}$\n")
    
    x = np.linspace(17, 20)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x, y, alpha=0.5, color='#ff5500')
    
    x1 = np.linspace(-7, -10)
    y = norm.pdf(x, means1, std1)
    ax.fill_between(x1, y, alpha=0.5, color='#ff5500')

    ax.annotate('at least 13.9%\n at leat 8 obs',xy=(250,0.0035), xytext=(250,0.0020),
            arrowprops={'arrowstyle': '-|>'}, va='center', color='black',fontsize=11)
   
    plt.xlim(-40, 40)
    plt.ylim(0, .07)
    plt.legend(fontsize=10)
    plt.title('Chebyshevs Theorem on the ROI \nof the R-rated Movies in the Drama Genre (n=55)',fontsize=14)
    plt.xlabel("ROI of R-rated Movies",fontsize=14)
    plt.ylabel("Density",fontsize=14)
    plt.show()

if __name__ == '__main__':
   main()


import seaborn as sns
sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.stripplot(data=df_roi_r, color='#ff5500');
sns.violinplot( data=df_roi_r,inner=None,color='0.8').set(title='KDE and Jittered strip plot\n on the ROI Percentage of the r-rated movies')
plt.show()


sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.swarmplot(data=df_roi_r, color='#ff5500');
sns.violinplot( data=df_roi_r, color='0.8', inner=None, aplha=.2).set(title='KDE and swarm plot\n on the ROI Percentage of the r-rated movies')
#sns.despine()
plt.show()


sns.set(font_scale=1.2)
plt.gcf().set_size_inches(5.8, 6)
sns.set_style("whitegrid")
sns.stripplot(data=df_roi_r, color='#ff5500', jitter=False)
sns.violinplot(data=df_roi_r,  split=True,inner=None,
      scale="count", color='0.8', alpha=.1).set(title='KDE and rug plot\n on the ROI Percentage of the r-rated movies')
#sns.despine()
plt.show()


freq_dis_per = freq_dis[:12].style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\1667078573.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_dis_per = freq_dis[:12].style.hide_index()\


dfi.export(freq_dis_per, 'freq_dis_per.png')


freq_dis_per1 = freq_dis[12:].style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\54156960.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_dis_per1 = freq_dis[12:].style.hide_index()\


dfi.export(freq_dis_per1, 'freq_dis_per1.png')


freq_cum_dis_per2 = freq_cum_dis2.style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black"),
                                      ("font-size", "10pt")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\2639483089.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  freq_cum_dis_per2 = freq_cum_dis2.style.hide_index()\


dfi.export(freq_cum_dis_per2, 'freq_cum_dis_per2.png')


cum_rel_freq_per2 = cum_rel_freq2.style.hide_index()\
            .set_table_styles([{'selector' : '','props' : [('border','3px solid grey')]},
            {"selector":"thead", 'props':[("background-color","#D3D3D3"),("color","black"),
                                         ("font-size" , "12pt")]},#headinig
            {'selector':"td", "props":[("background-color","white"), ("color"," black"),
                                      ("font-size", "10pt")]},#inside chart
            {'selector':'th.row_heading', 'props':[('background-color','white'),('color','black')]},
            {'selector':"td", "props":[('border-bottom','1px solid grey'),('border-right','1px solid grey')]},                                                                     ])

C:\Users\wisdom ovuike\AppData\Local\Temp\ipykernel_13940\572617805.py:1: FutureWarning: this method is deprecated in favour of `Styler.hide(axis="index")`
  cum_rel_freq_per2 = cum_rel_freq2.style.hide_index()\


dfi.export(cum_rel_freq_per2, 'cum_rel_freq_per2.png')


amount = [200, 400, 600, 800, 1000, 1200, 1400, 1600, 1800, 2000, 2200, 2400, 2600, 2800]
freq = [40, 53, 69, 76, 85, 89, 92, 94, 94, 96, 96, 96, 98, 100]
plt.plot( amount, freq ,color='red', marker='o')
plt.title('Cumulative relative frequency (%) of \n the ROI Percentage made on R-rated movies', fontsize=14)
plt.xlabel('Amount of ROI', fontsize=14)
plt.ylabel('Cumulative relative frequency (%)', fontsize=14)
plt.grid(True)
plt.show()


#                    Normal Distribution
import numpy as np
import matplotlib.pyplot as plt 

def make_gauss(N, sig, mu):
    return lambda x: N/(sig * (2*np.pi)**.5) * np.e ** (-(x-mu)**2/(2 * sig**2))

def main():
    ax = plt.figure().add_subplot(1,1,1)
    x = np.arange(-300, 300)
    s = [21,111,5.9]
    m = [16,60,5.1] 
    c = ['b','r','g']

    for sig, mu, color in zip(s, m, c): 
        gauss = make_gauss(1, sig, mu)(x)
        ax.plot(x, gauss, color, linewidth=2)

    plt.xlim(-300, 300)
    plt.ylim(0, 0.07)
    plt.title('Variability of the Cost, ROI, ROI Percentage of R-rated Movies\n Normal Distribution',fontsize=14)
    plt.xlabel("Values of the Cost, ROI, ROI Percent of R-rated Movies",fontsize=14)
    plt.ylabel("Density",fontsize=14)
    plt.legend(['Cost', 'ROI', 'RIO%'], loc='best')
    plt.grid(False)
    plt.show()

if __name__ == '__main__':
   main()


#<center><img  src="a1.png" style="width:23%"> <img src="a2.png" style="width:23%"> <img src="a3.png" style="width:23%"></center>
#<center><h3 style='color:#fbec5d'>System Rating R:</h3></center><p>The average RIO in system R rating is 21.10. Twenty movies in this rating are above the average, 
#which means 56% of the entire system R rating is above 21.10. The 3rd quantile of the ROI in this system rating is 33.40 meaning this is the most highest RIO, seven movies is above that making it 23% of the entire system R rating  
#<span style='color:#fbec5d'>For every dollar spent how mich did each movie make?.</span> This statement is assuming that if they were to all have the same budget which is a dollar, how much would each movie gnerate. 
#This objective is to cognize which movie is the most effcinet in each sysem rating and whcih susyem rating is the most efficient.


Drama_DataFrame


name = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x=='R'and Drama_DataFrame.Profit[i] > 0:
            name.append(Drama_DataFrame.Movie[i])
print(name)

['Django Unchained', 'Gone Girl', 'Priest', 'Fifty Shades Darker', 'Fifty Shades Freed', 'Crimson Peak', 'Zero Dark Thirty', 'Fifty Shades of Grey', 'The Master', 'Flight', 'The Ides of March', 'Nocturnal Animals', 'The Water Diviner', 'For Colored Girls', 'The Debt', 'Let Me In', 'Black Swan', 'Ex Machina', 'Room', 'If Beale Street Could Talk', 'Arbitrage', 'Stoker', 'Carol', 'Quartet', 'Hereditary', 'Melancholia', 'Manchester by the Sea', 'We Need to Talk About Kevin', 'Addicted', 'Mommy', 'Take Shelter', 'Boyhood', 'The Witch', 'Margin Call', 'Whiplash', 'Before Midnight', 'Silent House', "Winter's Bone", 'The Florida Project', 'We Are Your Friends', 'Locke', 'Knock Knock', 'Buried', 'Unsane', 'Blue Valentine', 'Martha Marcy May Marlene', 'Palo Alto', 'Sound of My Voice', 'A Ghost Story', 'Ordinary People', 'Fame', 'Endless Love', 'Ghost Story', 'Zoot Suit', 'Rich and Famous', 'Raggedy Man']


world_cur= []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='R'and Drama_DataFrame.Profit[i] > 0:
            world_cur.append(Drama_DataFrame.Worldwide_Gross_x[i])
print(world_cur)

['$449,948,323', '$368,567,189', '$84,154,026', '$381,398,492', '$371,350,619', '$74,966,854', '$134,612,435', '$570,998,101', '$50,647,416', '$160,558,438', '$77,735,925', '$32,398,681', '$31,054,727', '$38,017,873', '$46,604,054', '$28,270,399', '$331,266,710', '$38,358,392', '$36,262,783', '$19,859,167', '$35,830,713', '$12,034,913', '$42,843,521', '$56,178,935', '$70,133,905', '$21,817,298', '$77,733,867', '$10,765,283', '$17,499,242', '$17,536,004', '$4,972,016', '$57,273,049', '$40,454,520', '$20,433,227', '$38,969,037', '$23,251,930', '$16,610,760', '$16,131,551', '$11,295,324', '$10,153,415', '$2,088,390', '$6,328,516', '$21,270,290', '$14,244,931', '$16,566,240', '$5,438,911', '$1,156,309', '$429,448', '$2,769,782', '$54,766,923', '$77,211,836', '$34,718,173', '$1,951,683', '$3,256,082', '$13,000,000', '$11,000,000']


world_int = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='R'and Drama_DataFrame.Profit[i] > 0:
            world_int.append(Drama_DataFrame.Worldwide_Gross[i])
print(world_int)

[449948323, 368567189, 84154026, 381398492, 371350619, 74966854, 134612435, 570998101, 50647416, 160558438, 77735925, 32398681, 31054727, 38017873, 46604054, 28270399, 331266710, 38358392, 36262783, 19859167, 35830713, 12034913, 42843521, 56178935, 70133905, 21817298, 77733867, 10765283, 17499242, 17536004, 4972016, 57273049, 40454520, 20433227, 38969037, 23251930, 16610760, 16131551, 11295324, 10153415, 2088390, 6328516, 21270290, 14244931, 16566240, 5438911, 1156309, 429448, 2769782, 54766923, 77211836, 34718173, 1951683, 3256082, 13000000, 11000000]


profit_cur = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='R'and Drama_DataFrame.Profit[i] > 0:
            profit_cur.append(Drama_DataFrame.Profit_x[i])
print(profit_cur)

['$349,948,323', '$307,567,189', '$24,154,026', '$326,398,492', '$316,350,619', '$19,966,854', '$82,112,435', '$530,998,101', '$13,147,416', '$129,558,438', '$54,735,925', '$9,898,681', '$8,554,727', '$17,017,873', '$26,604,054', '$8,270,399', '$318,266,710', '$25,358,392', '$23,262,783', '$7,859,167', '$23,830,713', '$34,913', '$31,043,521', '$45,178,935', '$60,133,905', '$12,417,298', '$69,233,867', '$3,765,283', '$12,499,242', '$12,636,004', '$222,016', '$53,273,049', '$36,954,520', '$17,033,227', '$35,669,037', '$20,251,930', '$14,610,760', '$14,131,551', '$9,295,324', '$8,153,415', '$88,390', '$4,328,516', '$19,282,640', '$12,744,931', '$15,566,240', '$4,438,911', '$156,309', '$294,448', '$2,669,782', '$48,766,923', '$68,711,836', '$14,718,173', '$1,851,683', '$556,082', '$1,500,000', '$2,000,000']


profit_int = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x == 'R' and Drama_DataFrame.Profit[i] > 0:
            profit_int.append(int(Drama_DataFrame.Profit[i]))
print(profit_int)

[349948323, 307567189, 24154026, 326398492, 316350619, 19966854, 82112435, 530998101, 13147416, 129558438, 54735925, 9898681, 8554727, 17017873, 26604054, 8270399, 318266710, 25358392, 23262783, 7859167, 23830713, 34913, 31043521, 45178935, 60133905, 12417298, 69233867, 3765283, 12499242, 12636004, 222016, 53273049, 36954520, 17033227, 35669037, 20251930, 14610760, 14131551, 9295324, 8153415, 88390, 4328516, 19282640, 12744931, 15566240, 4438911, 156309, 294448, 2669782, 48766923, 68711836, 14718173, 1851683, 556082, 1500000, 2000000]


size = list('R'*56)
print(size)

['R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R']


npm = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x == 'R' and Drama_DataFrame.Profit[i] > 0:
            npm.append(int((Drama_DataFrame.Profit[i] / Drama_DataFrame.Worldwide_Gross[i])*100))
print(npm)

[77, 83, 28, 85, 85, 26, 60, 92, 25, 80, 70, 30, 27, 44, 57, 29, 96, 66, 64, 39, 66, 0, 72, 80, 85, 56, 89, 34, 71, 72, 4, 93, 91, 83, 91, 87, 87, 87, 82, 80, 4, 68, 90, 89, 93, 81, 13, 68, 96, 89, 88, 42, 94, 17, 11, 18]


npm_percent = []
for i in npm:
    npm_percent.append("{:}%".format(i))
print(npm_percent)

['77%', '83%', '28%', '85%', '85%', '26%', '60%', '92%', '25%', '80%', '70%', '30%', '27%', '44%', '57%', '29%', '96%', '66%', '64%', '39%', '66%', '0%', '72%', '80%', '85%', '56%', '89%', '34%', '71%', '72%', '4%', '93%', '91%', '83%', '91%', '87%', '87%', '87%', '82%', '80%', '4%', '68%', '90%', '89%', '93%', '81%', '13%', '68%', '96%', '89%', '88%', '42%', '94%', '17%', '11%', '18%']


r_rate = []
for i in list(range(56)):
    r_rate.append('Revenue')
for i in list(range(56)):
    r_rate.append('Profit')
print(r_rate)

['Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit']


name1 = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='PG'and Drama_DataFrame.Profit[i] > 0:
            name1.append(Drama_DataFrame.Movie[i])
print(name1)

['Hugo', 'Dolphin Tale', 'Wonder', 'The Last Song', 'War Room', 'The Lunchbox', 'Somewhere in Time', 'Urban Cowboy', 'Cinderella', 'War Room', 'Wonder', 'Little Women', 'Overcomer', 'The Jazz Singer', 'A Walk to Remember', 'Tuck Everlasting', 'Dreamer', 'The Lake House', 'Akeelah and the Bee', 'Bridge to Terabithia', 'August Rush', 'Fireproof', 'The Last Song', "God's Not Dead", "Mr. Holland's Opus", 'Phenomenon', 'Contact', 'The Spanish Prisoner', 'Sense and Sensibility', 'The Secret of Roan Inish', 'The Remains of the Day', 'Pure Country', 'Forever Young', 'A River Runs Through It', 'Honeysuckle Rose', 'Resurrection', 'Taps', 'On Golden Pond', 'Absence of Malice', 'The Night the Lights Went Out in Georgia', 'Rocky III', 'Tex', 'Staying Alive', 'Tender Mercies', 'Footloose', 'The Natural']


world_cur1 = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='PG'and Drama_DataFrame.Profit[i] > 0:
            world_cur1.append(Drama_DataFrame.Worldwide_Gross_x[i])
print(world_cur1)

['$180,047,784', '$96,068,724', '$304,604,712', '$92,678,948', '$73,975,239', '$12,231,500', '$9,709,597', '$46,918,287', '$542,351,353', '$73,986,904', '$305,937,718', '$216,601,214', '$38,102,988', '$27,118,000', '$47,494,916', '$19,344,615', '$38,741,732', '$114,830,111', '$18,948,425', '$137,587,063', '$64,605,762', '$33,473,297', '$89,137,047', '$64,667,874', '$106,269,971', '$152,036,382', '$171,120,329', '$13,835,130', '$134,582,776', '$6,101,815', '$63,954,968', '$15,164,458', '$127,956,187', '$43,440,294', '$17,815,212', '$157,297,525', '$35,856,053', '$119,285,432', '$40,716,963', '$14,923,752', '$125,052,686', '$549,368,315', '$64,892,670', '$8,443,124', '$80,008,942', '$48,000,000']


world_int1= []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='PG'and Drama_DataFrame.Profit[i] > 0:
            world_int1.append(Drama_DataFrame.Worldwide_Gross[i])
print(world_int1)

[180047784, 96068724, 304604712, 92678948, 73975239, 12231500, 9709597, 46918287, 542351353, 73986904, 305937718, 216601214, 38102988, 27118000, 47494916, 19344615, 38741732, 114830111, 18948425, 137587063, 64605762, 33473297, 89137047, 64667874, 106269971, 152036382, 171120329, 13835130, 134582776, 6101815, 63954968, 15164458, 127956187, 43440294, 17815212, 157297525, 35856053, 119285432, 40716963, 14923752, 125052686, 549368315, 64892670, 8443124, 80008942, 48000000]


profit_cur1 = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='PG'and Drama_DataFrame.Profit[i] > 0:
            profit_cur1.append(Drama_DataFrame.Profit_x[i])
print(profit_cur1)

['$47,784', '$59,068,724', '$284,604,712', '$72,678,948', '$70,975,239', '$10,531,500', '$4,609,597', '$36,918,287', '$447,351,353', '$70,986,904', '$285,937,718', '$176,601,214', '$33,102,988', '$26,696,000', '$35,694,916', '$4,344,615', '$6,741,732', '$74,830,111', '$10,948,425', '$120,587,063', '$34,605,762', '$32,973,297', '$69,137,047', '$62,667,874', '$83,269,971', '$120,036,382', '$81,120,329', '$3,835,130', '$118,582,776', '$3,101,815', '$48,954,968', '$5,164,458', '$107,956,187', '$31,440,294', '$12,815,212', '$150,297,525', '$21,856,053', '$104,285,432', '$28,716,963', '$7,423,752', '$108,052,686', '$544,368,315', '$42,892,670', '$3,943,124', '$71,808,942', '$20,000,000']


profit_int1 = []
for i,x in enumerate(Drama_DataFrame.Rating):
        if x =='PG'and Drama_DataFrame.Profit[i] > 0:
            profit_int1.append(int(Drama_DataFrame.Profit[i]))
print(profit_int1)

[47784, 59068724, 284604712, 72678948, 70975239, 10531500, 4609597, 36918287, 447351353, 70986904, 285937718, 176601214, 33102988, 26696000, 35694916, 4344615, 6741732, 74830111, 10948425, 120587063, 34605762, 32973297, 69137047, 62667874, 83269971, 120036382, 81120329, 3835130, 118582776, 3101815, 48954968, 5164458, 107956187, 31440294, 12815212, 150297525, 21856053, 104285432, 28716963, 7423752, 108052686, 544368315, 42892670, 3943124, 71808942, 20000000]


size_1 = []
for i in list(range(46)):
    size_1.append('PG')
print(size_1)

['PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG', 'PG']


npm1 = []
for i,x in enumerate(Drama_DataFrame.Rating):
    if x == 'PG'and Drama_DataFrame.Profit[i] > 0:
        npm1.append(int((Drama_DataFrame.Profit[i] / Drama_DataFrame.Worldwide_Gross[i])*100))
print(npm1)

[0, 61, 93, 78, 95, 86, 47, 78, 82, 95, 93, 81, 86, 98, 75, 22, 17, 65, 57, 87, 53, 98, 77, 96, 78, 78, 47, 27, 88, 50, 76, 34, 84, 72, 71, 95, 60, 87, 70, 49, 86, 99, 66, 46, 89, 41]


npm1_percent = []
for i in npm1:
    npm1_percent.append("{:}%".format(i))
print(npm1_percent)

['0%', '61%', '93%', '78%', '95%', '86%', '47%', '78%', '82%', '95%', '93%', '81%', '86%', '98%', '75%', '22%', '17%', '65%', '57%', '87%', '53%', '98%', '77%', '96%', '78%', '78%', '47%', '27%', '88%', '50%', '76%', '34%', '84%', '72%', '71%', '95%', '60%', '87%', '70%', '49%', '86%', '99%', '66%', '46%', '89%', '41%']


pg_rate = []
for i in list(range(46)):
    pg_rate.append('Revenue')
for i in list(range(46)):
    pg_rate.append('Profit')
print(pg_rate)

['Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Revenue', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit', 'Profit']

	id	release_date	movie	production_budget	domestic_gross	worldwide_gross
0	1	Dec 18, 2009	Avatar	$425,000,000	$760,507,625	$2,776,345,279
1	2	May 20, 2011	Pirates of the Caribbean: On Stranger Tides	$410,600,000	$241,063,875	$1,045,663,875
2	3	Jun 7, 2019	Dark Phoenix	$350,000,000	$42,762,350	$149,762,350
3	4	May 1, 2015	Avengers: Age of Ultron	$330,600,000	$459,005,868	$1,403,013,963
4	5	Dec 15, 2017	Star Wars Ep. VIII: The Last Jedi	$317,000,000	$620,181,382	$1,316,721,747

	id	release_date	movie	production_budget	domestic_gross_x	worldwide_gross	studio	domestic_gross_y	foreign_gross	year
0	2	May 20, 2011	Pirates of the Caribbean: On Stranger Tides	$410,600,000	$241,063,875	$1,045,663,875	BV	241100000.0	804600000	2011
1	4	May 1, 2015	Avengers: Age of Ultron	$330,600,000	$459,005,868	$1,403,013,963	BV	459000000.0	946400000	2015
2	7	Apr 27, 2018	Avengers: Infinity War	$300,000,000	$678,815,482	$2,048,134,200	BV	678800000.0	1,369.5	2018
3	9	Nov 17, 2017	Justice League	$300,000,000	$229,024,295	$655,945,209	WB	229000000.0	428900000	2017
4	10	Nov 6, 2015	Spectre	$300,000,000	$200,074,175	$879,620,923	Sony	200100000.0	680600000	2015

	id	release_date	movie	production_budget	domestic_gross_x	worldwide_gross	studio	domestic_gross_y	foreign_gross	year	movie_id	averagerating	numvotes	original_title	start_year	runtime_minutes	genres
0	2	May 20, 2011	Pirates of the Caribbean: On Stranger Tides	$410,600,000	$241,063,875	$1,045,663,875	BV	241100000.0	804600000	2011	tt1298650	6.6	447624	Pirates of the Caribbean: On Stranger Tides	2011	136.0	Action,Adventure,Fantasy
1	4	May 1, 2015	Avengers: Age of Ultron	$330,600,000	$459,005,868	$1,403,013,963	BV	459000000.0	946400000	2015	tt2395427	7.3	665594	Avengers: Age of Ultron	2015	141.0	Action,Adventure,Sci-Fi
2	7	Apr 27, 2018	Avengers: Infinity War	$300,000,000	$678,815,482	$2,048,134,200	BV	678800000.0	1,369.5	2018	tt4154756	8.5	670926	Avengers: Infinity War	2018	149.0	Action,Adventure,Sci-Fi
3	9	Nov 17, 2017	Justice League	$300,000,000	$229,024,295	$655,945,209	WB	229000000.0	428900000	2017	tt0974015	6.5	329135	Justice League	2017	120.0	Action,Adventure,Fantasy
4	10	Nov 6, 2015	Spectre	$300,000,000	$200,074,175	$879,620,923	Sony	200100000.0	680600000	2015	tt2379713	6.8	352504	Spectre	2015	148.0	Action,Adventure,Thriller

	id	release_date	movie	production_budget	domestic_gross_x	worldwide_gross	studio	domestic_gross_y	foreign_gross	year_x	...	score	votes	director	writer	star	country	budget	gross	company	runtime
0	4	May 1, 2015	Avengers: Age of Ultron	$330,600,000	$459,005,868	$1,403,013,963	BV	459000000.0	946400000	2015	...	7.3	777000.0	Joss Whedon	Joss Whedon	Robert Downey Jr.	United States	250000000.0	1.402810e+09	Marvel Studios	141.0
1	7	Apr 27, 2018	Avengers: Infinity War	$300,000,000	$678,815,482	$2,048,134,200	BV	678800000.0	1,369.5	2018	...	8.4	897000.0	Anthony Russo	Christopher Markus	Robert Downey Jr.	United States	321000000.0	2.048360e+09	Marvel Studios	149.0
2	9	Nov 17, 2017	Justice League	$300,000,000	$229,024,295	$655,945,209	WB	229000000.0	428900000	2017	...	6.1	418000.0	Zack Snyder	Jerry Siegel	Ben Affleck	United States	300000000.0	6.579270e+08	Warner Bros.	120.0
3	10	Nov 6, 2015	Spectre	$300,000,000	$200,074,175	$879,620,923	Sony	200100000.0	680600000	2015	...	6.8	393000.0	Sam Mendes	John Logan	Daniel Craig	United Kingdom	245000000.0	8.806815e+08	B24	148.0
4	11	Jul 20, 2012	The Dark Knight Rises	$275,000,000	$448,139,099	$1,084,439,099	WB	448100000.0	636800000	2012	...	8.4	1600000.0	Christopher Nolan	Jonathan Nolan	Christian Bale	United Kingdom	250000000.0	1.081143e+09	Warner Bros.	164.0

	movie	rating	genre	year	released	score	votes	director	writer	star	country	budget	gross	company	runtime
0	La traviata	G	Drama	1982	February 18, 1983 (Italy)	7.2	1300.0	Franco Zeffirelli	Francesco Maria Piave	Teresa Stratas	Netherlands	NaN	3783329.0	Accent Films B.V.	109.0
1	A Sunday in the Country	G	Drama	1984	April 11, 1984 (France)	7.6	2500.0	Bertrand Tavernier	Pierre Bost	Louis Ducreux	France	NaN	2411143.0	Films A2	90.0
2	Babette's Feast	G	Drama	1987	March 4, 1988 (United States)	7.8	19000.0	Gabriel Axel	Karen Blixen	Stéphane Audran	Denmark	NaN	4637920.0	Panorama Film A/S	103.0
3	Little Dorrit	G	Drama	1987	October 21, 1988 (United States)	7.3	1000.0	Christine Edzard	Charles Dickens	Derek Jacobi	United Kingdom	NaN	1025228.0	Sands	357.0
4	Prancer	G	Drama	1989	November 17, 1989 (United States)	6.4	4800.0	John D. Hancock	Greg Taylor	Sam Elliott	United States	NaN	18587135.0	Cineplex Odeon Films	103.0
5	Wild Hearts Can't Be Broken	G	Drama	1991	May 24, 1991 (United States)	7.2	5000.0	Steve Miner	Matt Williams	Gabrielle Anwar	United States	NaN	7294835.0	Walt Disney Pictures	88.0
6	The Secret Garden	G	Drama	1993	August 13, 1993 (United States)	7.3	38000.0	Agnieszka Holland	Frances Hodgson Burnett	Kate Maberly	United Kingdom	18000000.0	31181347.0	Warner Bros.	101.0
7	Through the Olive Trees	G	Drama	1994	January 25, 1995 (France)	7.8	7100.0	Abbas Kiarostami	Abbas Kiarostami	Mohamad Ali Keshavarz	Iran	NaN	NaN	Abbas Kiarostami Productions	103.0
8	A Little Princess	G	Drama	1995	May 19, 1995 (United States)	7.7	33000.0	Alfonso Cuarón	Frances Hodgson Burnett	Liesel Matthews	United States	17000000.0	10015449.0	Warner Bros.	97.0
9	The Winslow Boy	G	Drama	1999	October 29, 1999 (United Kingdom)	7.3	7500.0	David Mamet	Terence Rattigan	Rebecca Pidgeon	United Kingdom	NaN	3957934.0	Winslow Partners Ltd.	104.0
10	The Rookie	G	Drama	2002	March 29, 2002 (United States)	6.9	33000.0	John Lee Hancock	Mike Rich	Dennis Quaid	United States	22000000.0	80693537.0	98 MPH Productions	127.0

	movie	rating	genre	year	released	score	votes	director	writer	star	country	budget	gross	company	runtime
0	The Shining	R	Drama	1980	June 13, 1980 (United States)	8.4	927000.0	Stanley Kubrick	Stephen King	Jack Nicholson	United Kingdom	19000000.0	46998772.0	Warner Bros.	146.0
1	The Blue Lagoon	R	Adventure	1980	July 2, 1980 (United States)	5.8	65000.0	Randal Kleiser	Henry De Vere Stacpoole	Brooke Shields	United States	4500000.0	58853106.0	Columbia Pictures	104.0
2	Star Wars: Episode V - The Empire Strikes Back	PG	Action	1980	June 20, 1980 (United States)	8.7	1200000.0	Irvin Kershner	Leigh Brackett	Mark Hamill	United States	18000000.0	538375067.0	Lucasfilm	124.0
3	Airplane!	PG	Comedy	1980	July 2, 1980 (United States)	7.7	221000.0	Jim Abrahams	Jim Abrahams	Robert Hays	United States	3500000.0	83453539.0	Paramount Pictures	88.0
4	Caddyshack	R	Comedy	1980	July 25, 1980 (United States)	7.3	108000.0	Harold Ramis	Brian Doyle-Murray	Chevy Chase	United States	6000000.0	39846344.0	Orion Pictures	98.0

	movie_id	movie	original_title	start_year	runtime_minutes	genres
0	tt0063540	Sunghursh	Sunghursh	2013	175.0	Action,Crime,Drama
1	tt0066787	One Day Before the Rainy Season	Ashad Ka Ek Din	2019	114.0	Biography,Drama
2	tt0069049	The Other Side of the Wind	The Other Side of the Wind	2018	122.0	Drama
3	tt0069204	Sabse Bada Sukh	Sabse Bada Sukh	2018	NaN	Comedy,Drama
4	tt0100275	The Wandering Soap Opera	La Telenovela Errante	2017	80.0	Comedy,Drama,Fantasy

	movie_id	averagerating	numvotes
0	tt10356526	8.3	31
1	tt10384606	8.9	559
2	tt1042974	6.4	20
3	tt1043726	4.2	50352
4	tt1060240	6.5	21

	movie	studio	domestic_gross	foreign_gross	year
0	Toy Story 3	BV	415000000.0	652000000	2010
1	Alice in Wonderland (2010)	BV	334200000.0	691300000	2010
2	Harry Potter and the Deathly Hallows Part 1	WB	296000000.0	664300000	2010
3	Inception	WB	292600000.0	535700000	2010
4	Shrek Forever After	P/DW	238700000.0	513900000	2010

	movie_id	averagerating	numvotes	movie	original_title	start_year	runtime_minutes	genres
0	tt10356526	8.3	31	Laiye Je Yaarian	Laiye Je Yaarian	2019	117.0	Romance
1	tt10384606	8.9	559	Borderless	Borderless	2019	87.0	Documentary
2	tt1042974	6.4	20	Just Inès	Just Inès	2010	90.0	Drama
3	tt1043726	4.2	50352	The Legend of Hercules	The Legend of Hercules	2014	99.0	Action,Adventure,Fantasy
4	tt1060240	6.5	21	Até Onde?	Até Onde?	2011	73.0	Mystery,Thriller

	Movie	Release_Date	Genre	Rating	Production_Budget	Production_Budget_x	Domestic_Gross	Domestic_Gross_x	Foreign_Gross	Foreign_Gross_x	...	Profit_x	Tickets	Tickets_x	Runtime	Averagerating	Company	Studio	Star	Director	Writer
0	Hugo	Nov 23, 2011	Drama	PG	180000000	$180,000,000	73864507	$73,864,507	111900000.0	$111,900,000	...	$47,784	18004778	18,004,778	126.0	7.5	Paramount Pictures	Par.	Asa Butterfield	Martin Scorsese	John Logan
1	Hugo	Nov 23, 2011	Drama	PG	180000000	$180,000,000	73864507	$73,864,507	111900000.0	$111,900,000	...	$47,784	18004778	18,004,778	126.0	7.9	Paramount Pictures	Par.	Asa Butterfield	Martin Scorsese	John Logan
2	The Wolfman	Feb 12, 2010	Drama	R	150000000	$150,000,000	62189884	$62,189,884	77800000.0	$77,800,000	...	$-7,365,642	14263436	14,263,436	NaN	5.8	NaN	Uni.	Benicio Del Toro	Joe Johnston	Andrew Kevin Walker
3	Gravity	Oct 4, 2013	Drama	PG-13	110000000	$110,000,000	274092705	$274,092,705	449100000.0	$449,100,000	...	$583,698,673	69369867	69,369,867	91.0	7.7	Warner Bros.	WB	Sandra Bullock	Alfonso Cuarón	Alfonso Cuarón
4	Django Unchained	Dec 25, 2012	Drama	R	100000000	$100,000,000	162805434	$162,805,434	262600000.0	$262,600,000	...	$349,948,323	44994832	44,994,832	165.0	8.4	The Weinstein Company	Wein.	Jamie Foxx	Quentin Tarantino	Quentin Tarantino
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
195	Like Crazy	Oct 28, 2011	Drama	PG-13	250000	$250,000	3395391	$3,395,391	336000.0	$336,000	...	$3,478,400	372840	372,840	86.0	7.2	Paramount Vantage	ParV	Felicity Jones	Drake Doremus	Drake Doremus
196	The Canyons	Aug 2, 2013	Drama	R	250000	$250,000	59671	$59,671	NaN	NaN	...	$-187,625	6238	6,238	99.0	3.8	Prettybird	IFC	Lindsay Lohan	Paul Schrader	Bret Easton Ellis
197	Another Earth	Jul 22, 2011	Drama	PG-13	175000	$175,000	1321194	$1,321,194	456000.0	$456,000	...	$1,927,779	210278	210,278	92.0	7.0	Artists Public Domain	FoxS	Brit Marling	Mike Cahill	Mike Cahill
198	Sound of My Voice	Apr 27, 2012	Drama	R	135000	$135,000	408015	$408,015	NaN	NaN	...	$294,448	42945	42,945	85.0	6.6	Skyscraper Films	FoxS	Christopher Denham	Zal Batmanglij	Zal Batmanglij
199	A Ghost Story	Jul 7, 2017	Drama	R	100000	$100,000	1594798	$1,594,798	NaN	NaN	...	$2,669,782	276978	276,978	92.0	6.8	Sailor Bear	A24	Casey Affleck	David Lowery	David Lowery

	movie	rating	genre	year	released	score	votes	director	writer	star	country	budget	gross	company	runtime
0	Somewhere in Time	PG	Drama	1980	October 3, 1980 (United States)	7.2	27000.0	Jeannot Szwarc	Richard Matheson	Christopher Reeve	United States	5100000.0	9709597.0	Rastar Pictures	103.0
1	Urban Cowboy	PG	Drama	1980	June 6, 1980 (United States)	6.4	14000.0	James Bridges	Aaron Latham	John Travolta	United States	NaN	46918287.0	Paramount Pictures	132.0
2	Cattle Annie and Little Britches	PG	Drama	1980	April 24, 1981 (United States)	6.1	604.0	Lamont Johnson	David Eyre	Scott Glenn	United States	5100000.0	534816.0	Cattle Annie Productions	97.0
3	The Jazz Singer	PG	Drama	1980	December 19, 1980 (United States)	5.9	4000.0	Richard Fleischer	Samson Raphaelson	Laurence Olivier	United States	NaN	27118000.0	EMI Films	115.0
4	The Competition	PG	Drama	1980	December 3, 1980 (United States)	6.7	1900.0	Joel Oliansky	Joel Oliansky	Richard Dreyfuss	United States	NaN	14287755.0	Rastar Films	123.0

	movie	rating	genre	year	released	score	votes	director	writer	star	country	budget	gross	company	runtime
0	Matador	NC-17	Drama	1986	March 7, 1986 (Spain)	7.0	11000.0	Pedro Almodóvar	Pedro Almodóvar	Assumpta Serna	Spain	NaN	286126.0	Compañía Iberoamericana de TV	110.0
1	Whore	NC-17	Drama	1991	October 18, 1991 (United States)	5.6	3500.0	Ken Russell	David Hines	Theresa Russell	United States	NaN	1008404.0	Cheap Date	85.0
2	Tokyo Decadence	NC-17	Drama	1992	April 30, 1993 (United States)	6.0	3000.0	Ryû Murakami	Ryû Murakami	Miho Nikaido	Japan	NaN	277845.0	Cinemabrain	112.0
3	Wide Sargasso Sea	NC-17	Drama	1993	April 16, 1993 (United States)	5.7	1900.0	John Duigan	Jan Sharp	Karina Lombard	Australia	NaN	1614784.0	Laughing Kookaburra Productions	98.0
4	Kids	NC-17	Drama	1995	September 1, 1995 (United States)	7.1	75000.0	Larry Clark	Harmony Korine	Leo Fitzpatrick	United States	1500000.0	7412216.0	Guys Upstairs	91.0
5	Showgirls	NC-17	Drama	1995	September 22, 1995 (United States)	4.9	64000.0	Paul Verhoeven	Joe Eszterhas	Elizabeth Berkley	France	45000000.0	20358624.0	Carolco Pictures	128.0
6	Crash	NC-17	Drama	1996	March 21, 1997 (United States)	6.4	54000.0	David Cronenberg	J.G. Ballard	James Spader	Canada	9000000.0	2671291.0	Alliance Communications Corporation	100.0
7	Bent	NC-17	Drama	1997	November 26, 1997 (United States)	7.2	7900.0	Sean Mathias	Martin Sherman	Lothaire Bluteau	United Kingdom	NaN	496059.0	Channel Four Films	105.0
8	The Dreamers	NC-17	Drama	2003	February 20, 2004 (United States)	7.2	114000.0	Bernardo Bertolucci	Gilbert Adair	Michael Pitt	United Kingdom	15000000.0	24152155.0	Recorded Picture Company (RPC)	115.0
9	Ma mère	NC-17	Drama	2004	May 19, 2004 (France)	5.1	6600.0	Christophe Honoré	Georges Bataille	Isabelle Huppert	France	NaN	1510052.0	Gemini Films	110.0
10	Lust, Caution	NC-17	Drama	2007	October 26, 2007 (United States)	7.5	38000.0	Ang Lee	Eileen Chang	Tony Chiu-Wai Leung	Taiwan	15000000.0	67091915.0	Haishang Films	157.0
11	Shame	NC-17	Drama	2011	January 13, 2012 (United Kingdom)	7.2	187000.0	Steve McQueen	Steve McQueen	Michael Fassbender	United Kingdom	6500000.0	19123767.0	Fox Searchlight Pictures	101.0
12	Elles	NC-17	Drama	2011	February 1, 2012 (France)	5.6	6700.0	Malgorzata Szumowska	Tine Byrckel	Juliette Binoche	France	NaN	3822241.0	Slot Machine	99.0
13	Blue Is the Warmest Colour	NC-17	Drama	2013	October 9, 2013 (Belgium)	7.7	142000.0	Abdellatif Kechiche	Abdellatif Kechiche	Léa Seydoux	France	NaN	19465835.0	Quat'sous Films	180.0

	movie	rating	genre	year	released	score	votes	director	writer	star	country	budget	gross	company	runtime
0	Ordinary People	R	Drama	1980	September 19, 1980 (United States)	7.7	49000.0	Robert Redford	Judith Guest	Donald Sutherland	United States	6000000.0	54766923.0	Paramount Pictures	124.0
1	Fame	R	Drama	1980	May 16, 1980 (United States)	6.6	21000.0	Alan Parker	Christopher Gore	Eddie Barth	United States	NaN	21202829.0	Metro-Goldwyn-Mayer (MGM)	134.0
2	Windows	R	Drama	1980	January 18, 1980 (United States)	4.8	643.0	Gordon Willis	Barry Siegel	Talia Shire	United States	NaN	2128395.0	Mike Lobell Productions	96.0
3	Endless Love	R	Drama	1981	July 17, 1981 (United States)	4.9	7600.0	Franco Zeffirelli	Scott Spencer	Brooke Shields	United States	NaN	32492674.0	PolyGram Filmed Entertainment	116.0
4	Ghost Story	R	Drama	1981	December 18, 1981 (United States)	6.3	7900.0	John Irvin	Peter Straub	Craig Wasson	United States	NaN	23371905.0	Universal Pictures	110.0
5	One from the Heart	R	Drama	1981	February 11, 1982 (United States)	6.5	5700.0	Francis Ford Coppola	Armyan Bernstein	Frederic Forrest	United States	26000000.0	636796.0	Zoetrope Studios	107.0
6	The Hand	R	Drama	1981	April 24, 1981 (United States)	5.5	5700.0	Oliver Stone	Marc Brandel	Michael Caine	United States	NaN	2447576.0	Orion Pictures	104.0
7	Pennies from Heaven	R	Drama	1981	January 1, 1982 (United States)	6.5	5300.0	Herbert Ross	Dennis Potter	Steve Martin	United States	22000000.0	9171289.0	Metro-Goldwyn-Mayer (MGM)	108.0
8	Zoot Suit	R	Drama	1981	January 1, 1982 (United States)	6.8	1100.0	Luis Valdez	Luis Valdez	Daniel Valdez	United States	2700000.0	3256082.0	Universal Pictures	103.0
9	Rich and Famous	R	Drama	1981	October 9, 1981 (United States)	5.9	1600.0	George Cukor	Gerald Ayres	Jacqueline Bisset	United States	NaN	14492125.0	Jaquet	117.0
10	Raggedy Man	R	Drama	1981	September 18, 1981 (United States)	6.8	1400.0	Jack Fisk	William D. Wittliff	Sissy Spacek	United States	NaN	1976198.0	Universal Pictures	94.0

	Movie	Release_Date	Genre	Rating	Production_Budget	Production_Budget_x	Domestic_Gross	Domestic_Gross_x	Foreign_Gross	Foreign_Gross_x	...	Profit	Profit_x	Tickets	Tickets_x	Runtime	Averagerating	Company	Star	Director	Writer
0	Beauty and the Beast 1991	Novemeber 22, 1991	Drama	G	20000000	$20,000,000	206333165	$206,333,165	232323678	$232,323,678	...	418656843	$418,656,843	43865684	43,865,684	84	8.0	The Walt Disney Company	Paige O'Hara	Gary Trousdale	Linda Woolverton
1	The Little Rascals	August 5, 1994	Drama	G	23000000	$23,000,000	51764950	$51,764,950	15183000	$15,183,000	...	43947950	$43,947,950	6694795	6,694,795	83	6.3	Universal Pictures	Brittany Ashton	Penelope Spheeris	Penelope Spheeris
2	Ramona and Beezus	July 23, 2010	Drama	G	15000000	$15,000,000	25167002	$25,167,002	1302619	$1,302,619	...	12469621	$12,469,621	2746962	2,746,962	103	6.5	Fox 2000 Pictures	Joey King	Elizabeth Allen Ressenbaum	Beverly Cleary
3	The Black Stallion	October 17, 1979	Drama	G	2700000	$2,700,000	0	$0	0	$0	...	35099643	$35,099,643	3779964	3,779,964	118	7.4	Omni Zoetrope	Kelly Reno	Carral Ballard	Melissa Mathison
4	The Hunchback of Notre Drame	June 21, 1996	Drama	G	70000000	$70,000,000	100138851	$100,138,851	225361149	$225,361,149	...	255500000	$255,500,000	32550000	32,550,000	91	7.0	The Walt Disney Company	Demi Moore	Gary Trouside	Victor Hugo

	Movie	Release_Date	Genre	Rating	Production_Budget	Production_Budget_x	Domestic_Gross	Domestic_Gross_x	Foreign_Gross	Foreign_Gross_x	...	Profit	Profit_x	Tickets	Tickets_x	Runtime	Averagerating	Company	Star	Director	Writer
0	Showgirls	September 22, 1995	Drama	NC-17	45000000	$45,000,000	20350754	$20,350,754	17400000	$17,400,000	...	-7249246	$-7,249,246	3775075	3,775,075	97	4.9	Carolco Pictures	Elizabeth Berkley	Paul Verhoeven	Joe Eszterhas
1	The Dreamers	February 6, 2004	Drama	NC-17	15000000	$15,000,000	2531462	$2,531,462	12775651	$12,775,651	...	307113	$307,113	1530711	1,530,711	130	7.1	Recorded Picture Company	Eva Green	Bernardo Bertolucci	Gilbert Adair
2	Shame	December 2, 2011	Drama	NC-17	6500000	$6,500,000	4002293	$4,002,293	16410548	$16,410,548	...	13912841	$13,912,841	2041284	2,041,284	101	7.2	Film4	Michael Fassbender	Steve McQueen	Abi Morgan
3	Blue Is the Warmest Colour	October 25, 2013	Drama	NC-17	4074940	$4,074,940	2199787	$2,199,787	17266048	$17,266,048	...	15390895	$15,390,895	1946584	1,946,584	180	7.7	Wild Bunch	Léa Seydoux	Abdellatif Kechiche	Ghalia Lacroix
4	Blue Valentine	December 29, 2010	Drama	NC-17	1000000	$1,000,000	9737892	$9,737,892	6828348	$6,828,348	...	15566240	$15,566,240	1656624	1,656,624	120	7.4	Hunting Lane Films	Ryan Gosling	Derek Cianfrance	Cami Delavigne

	Name	Revenue	Profit	Net Profit Margin %
0	Stoker	$12,034,913	$34,913	0%
1	Take Shelter	$4,972,016	$222,016	4%
2	Take Shelter	$4,972,016	$222,016	4%
3	Rich and Famous	$13,000,000	$1,500,000	11%
4	Palo Alto	$1,156,309	$156,309	13%
5	Zoot Suit	$3,256,082	$556,082	17%
6	Raggedy Man	$11,000,000	$2,000,000	18%
7	The Master	$50,647,416	$13,147,416	25%
8	Crimson Peak	$74,966,854	$19,966,854	26%
9	The Water Diviner	$31,054,727	$8,554,727	27%

	Name	Revenue	Profit	Net Profit Margin %
0	Hugo	$180,047,784	$47,784	0%
1	Dreamer	$38,741,732	$6,741,732	17%
2	Tuck Everlasting	$19,344,615	$4,344,615	22%
3	The Spanish Prisoner	$13,835,130	$3,835,130	27%
4	Pure Country	$15,164,458	$5,164,458	34%
5	The Natural	$48,000,000	$20,000,000	41%
6	Tender Mercies	$8,443,124	$3,943,124	46%
7	Somewhere in Time	$9,709,597	$4,609,597	47%
8	The Night the Lights...	$14,923,752	$7,423,752	49%
9	The Secret of Roan Inish	$6,101,815	$3,101,815	50%

	Name	Revenue	Profit	Net Profit Margin %
0	Pollyanna	$3,750,000	$1,250,000	33%
1	Charlotte's Web	$143,985,708	$58,985,708	40%
2	Kit Kittredge: An American Girl	$17,657,973	$7,657,973	43%
3	Ramona and Beezus	$27,469,621	$12,469,621	45%
4	Prancer	$18,587,135	$11,587,135	62%
5	The Little Rascals	$66,947,950	$43,947,950	65%
6	A Sunday in the Country	$2,411,143	$1,711,143	70%
7	The Rookie	$80,693,537	$58,693,537	72%
8	My Fair Lady 1964	$72,071,636	$55,071,636	76%
9	The Hunchback of Notre Drame	$325,500,000	$255,500,000	78%

	Name	Revenue	Profit	Net Profit Margin %
0	Charlie St. Cloud	$48,478,084	$4,478,084	9%
1	The Light Between Oceans	$22,281,732	$2,281,732	10%
2	Draft Day	$29,847,480	$4,847,480	16%
3	Rabbit Hole	$6,205,034	$1,205,034	19%
4	Country Strong	$20,601,987	$5,601,987	27%
5	Anna Karenina	$71,004,627	$22,004,627	30%
6	The Best of Me	$41,059,418	$15,059,418	36%
7	Burlesque	$90,552,675	$35,552,675	39%
8	The Tree of Life	$61,721,826	$26,721,826	43%
9	The Longest Ride	$63,802,928	$29,802,928	46%

	Name	Revenue	Profit	Net Profit Margin %
0	Whore	$1,008,404	$8,404	0%
1	Whore	$1,008,404	$8,404	0%
2	The Dreamers	$15,307,113	$307,113	2%
3	Elles	$3,822,241	$256,669	6%
4	Matador	$17,356,268	$4,856,268	27%
5	Natural Born Killers	$50,283,563	$16,283,563	32%
6	Wide Sargasso Sea	$1,614,784	$659,312	40%
7	Bad Lieutenant	$2,038,916	$1,038,916	50%
8	Two Girls and a Guy	$2,315,026	$1,315,026	56%
9	Law of Desire	$1,470,809	$858,737	58%

	Budget	Season	Profit	Name	No.Tickets	ROI	NPM	System
0	100000000.0	1	349948323	Django Unchained	44994832	350.0	77	R
1	61000000.0	4	307567189	Gone Girl	36856719	504.0	83	R
2	60000000.0	2	24154026	Priest	8415403	40.0	28	R
3	55000000.0	1	326398492	Fifty Shades Darker	38139849	593.0	85	R
4	55000000.0	1	316350619	Fifty Shades Freed	37135062	575.0	85	R
...	...	...	...	...	...	...	...	...
220	12000.0	2	401802	Pink Flamingos	41380	3348.0	97	NC-17
221	15000000.0	4	50167430	Lust, Caution	6516743	334.0	76	NC-17
222	2200000.0	4	3546453	Happiness 1998	574645	161.0	61	NC-17
223	50000.0	4	958404	Whore 1991	100840	1917.0	95	NC-17
224	612072.0	2	858737	Law of Desire	147081	140.0	58	NC-17

Objective

Datasets

Approaches

Insights

The Audience

G Rated Movies

PG Rated Movies

PG-13 Rated Movies

R Rated Movies

NC-17 Rated Movies

Technical Approach

1. Return on Investment or ROI

Blueprint:

Analysis

The Distribution of the Budgets of all the R-rated movies in the Drama genre.

The Variance of the Budgets of all the R-rated movies in the Drama genre.

The Variance with Standard Deviations of the Budgets of all the R-rated movies in the Drama genre.

The Distribution of the Budgets of all the R-rated movies in the Drama genre.

The Variance of the Budgets of all the R-rated movies in the Drama genre.

The Skewness of the Budgets of all the R-rated Movies in the Drama genre.

The Mean, Median and Mode in relation to the Skewness of all the R-rated Movies in the Drama genre.

The Mean, Median and Mode in relation to the Skewness of all the R-rated Movies in the Drama genre.

The Kernel Density Estimate on the Skewness of the Budgets of all the R-rated movies in the Drama genre.

The Distribution using the Violin Plot and Jittered plot of all the R-rated Movies in the Drama Genre

The Distribution using the Violin Plot and Swarm plot of all the R-rated Movies in the Drama Genre.

The Distribution using the Violin Plot and Rug plot of all the R-rated movies in the Drama Genre

The Central Tendency using the Violin Plot and Box plot of all the R-rated movies in the Drama Genre

Frequency Distribution Table of all the R-rated Movies in the Drama Genre

Cumulative Frequency Distribution Table of all the R-rated Movies in the Drama Genre

The Bernoulli Distribution of the Budgets of R-rated Drama Movies that are Micro-Budgets

The Bernoulli Distribution of the Budgets of R-rated Drama Movies that are Low-Budgets

The Bernoulli Distribution of the Budgets of R-rated Drama Movies that are Mid-Budgets

The Bernoulli Distribution of the Budgets of R-rated Drama Movies that are High-Budgets

The Bernoulli Distribution of on the Sub-groups within the Budgets of R-rated Drama Movies that are Micro-Budgets

The Skewness of the Budgets of all the R-rated Movies in the Drama genre.

The Mean, Median and Mode in relation to the Skewness of all the R-rated Movies in the Drama genre.

The Kernel Density Estimate on the Skewness of the Budgets of all the R-rated movies in the Drama genre.

System Rating G:

System Rating PG:

System Rating PG-13:

System Rating NR:

Net Profit Margin¶

A Dataframe on the Net Profit Margin of R-rated Drama Movies

A Dataframe on the Net Profit Margin of PG-rated Drama Movies

A Dataframe on the Net Profit Margin of G-rated Drama Movies

A Dataframe on the Net Profit Margin of PG-13 rated Drama Movies

A Dataframe on the Net Profit Margin of NC-17 rated Drama Movies

Blueprint: Budget and Revenue of Movies¶

Blueprint: Revenue of Movies¶

Blueprint: Budget of Movies¶

Analysis

The Average Budgets of all the R-rated Movies in the Drama genre.

The Average Revenue of all the R-rated Movies in the Drama genre.

The Average Rating of all the R-rated Movies in the Drama genre.

Blueprint: Movies that made Profit¶

Blueprint:

Analysis

Blueprint: Movies that did not make any Profit.¶

Blueprint: Top 20 Highest Profitable Movies and Top 20 Lowest Profitable Movies¶

Blueprint: What Movie is the most Successful.¶

Analysis

Blueprint: Number of Tickets Sold.¶

The Distribution of the Budgets of
all the R-rated movies in the Drama genre.

The Variance of the Budgets of all the
R-rated movies in the Drama genre.

The Variance with Standard Deviations of the
Budgets of all the R-rated movies in the Drama genre.

The Distribution of the Budgets
of all the R-rated movies in the Drama genre.

The Variance of the Budgets
of all the R-rated movies in the Drama genre.

The Skewness of the Budgets of
all the R-rated Movies in the Drama genre.

The Mean, Median and Mode in relation to the
Skewness of all the R-rated Movies in the Drama genre.

The Mean, Median and Mode in relation to the
Skewness of all the R-rated Movies in the Drama genre.

The Kernel Density Estimate on the Skewness of the
Budgets of all the R-rated movies in the Drama genre.

The Distribution using the Violin Plot and
Jittered plot of all the R-rated Movies in the Drama Genre

The Distribution using the Violin Plot and
Swarm plot of all the R-rated Movies in the Drama Genre.

The Distribution using the Violin Plot and
Rug plot of all the R-rated movies in the Drama Genre

The Central Tendency using the Violin Plot and
Box plot of all the R-rated movies in the Drama Genre

Frequency Distribution Table
of all the R-rated Movies in the Drama Genre

Cumulative Frequency Distribution Table
of all the R-rated Movies in the Drama Genre

The Bernoulli Distribution of the Budgets
of R-rated Drama Movies that are Micro-Budgets

The Bernoulli Distribution of the Budgets
of R-rated Drama Movies that are Low-Budgets

The Bernoulli Distribution of the Budgets
of R-rated Drama Movies that are Mid-Budgets

The Bernoulli Distribution of the Budgets
of R-rated Drama Movies that are High-Budgets

The Skewness of the Budgets of
all the R-rated Movies in the Drama genre.

The Mean, Median and Mode in relation to the
Skewness of all the R-rated Movies in the Drama genre.

The Kernel Density Estimate on the Skewness of the
Budgets of all the R-rated movies in the Drama genre.

The Average Budgets of
all the R-rated Movies in the Drama genre.

The Average Revenue of
all the R-rated Movies in the Drama genre.

The Average Rating of
all the R-rated Movies in the Drama genre.